Skills learn
📦
learn
v2.0 Content revision r1 Critical 🌐 Network access📁 Filesystem access⚡ Contains scripts⚙️ External commands🔑 Env variables
Install Agent Skills Mid-Conversation
Agents often need specialized instructions that are not loaded at the start of a session. This skill lets Claude, Codex, and Claude Code search, preview, scan, install, update, remove, and rate skills from agentskill.sh.
Supports: Claude Codex Code(CC)
Do not auto-install this skill.
The canonical policy requires operator review before any installation action.
Install with my Agent
Copy this request to your Agent. It includes the canonical Skill page and manifest.
Agent request
Review the Skillstore skill "learn" from https://skillstore.io/skills/agentskill-sh-learn.md and its manifest at https://skillstore.io/api/skills/agentskill-sh-learn/manifest. Verify the artifact. Do not auto-install. Inspect the skill and report your findings, then wait for an operator or manual installation decision.Your Agent should still show its plan and request any confirmation required by the security policy.
Agent-readable resources
Use these links when an AI agent, crawler, or script needs clean context instead of reading the full page.
Test it
Using "learn". /learn documentation
Expected outcome:
A ranked table of matching skills with authors, install counts, security scores, short descriptions, and an interactive install choice.
Using "learn". /learn scan ./SKILL.md
Expected outcome:
A security report that lists the score, detected issues, network endpoints, file access, shell commands, and an allow or block recommendation.
Using "learn". /learn update
Expected outcome:
A summary of installed skills, update status, security rescan results, and a confirmation prompt before applying updates.
Security Audit
Criticalv7 • 7/9/2026 Open versioned report
Most static hits are false positives from documentation and defensive scanner examples, especially references/SECURITY.md and Markdown inline-code in SKILL.md. The real risks are the intended remote marketplace behavior: fetching and installing remote skill content into agent directories, self-updating the installer, and sending feedback or scan reports to agentskill.sh.
4
Files scanned
1,630
Lines analyzed
115
Review items
0
False positives ignored
Confirmed security concerns (8)
Critical
[HEURISTIC] DANGEROUS COMBINATION: Code execution + Network + Credential access
This combination is common in credential stealers and RATs
The aggregate combination is real because the skill combines external marketplace fetching with writes to agent skill directories and optional telemetry. The intent is legitimate, but the combined behavior creates supply-chain risk.
Critical
[HEURISTIC] DANGEROUS COMBINATION: Network + Credentials + Evasion techniques
This combination suggests data exfiltration with anti-detection
The aggregate combination is real because the skill combines external marketplace fetching with writes to agent skill directories and optional telemetry. The intent is legitimate, but the combined behavior creates supply-chain risk.
High
[HEURISTIC] SUSPICIOUS COMBINATION: Code execution + Persistence mechanism
This combination is common in malware that maintains access
The aggregate combination is real because the skill combines external marketplace fetching with writes to agent skill directories and optional telemetry. The intent is legitimate, but the combined behavior creates supply-chain risk.
High
[HEURISTIC] SUSPICIOUS COMBINATION: Filesystem + Credentials + Network
This combination could indicate credential harvesting and exfiltration
The aggregate combination is real because the skill combines external marketplace fetching with writes to agent skill directories and optional telemetry. The intent is legitimate, but the combined behavior creates supply-chain risk.
High
Remote Skill Installation Can Change Agent Behavior
The install flow fetches skill content from agentskill.sh, scans it, and writes it into the detected agent skill directory. A compromised marketplace response or weak scan result could install instructions that influence future agent behavior.
The cited install flow explicitly fetches remote skill content, scans it, writes a skill file, and tracks the install. This is intended behavior, but it is a clear supply-chain control point.
High
Self-Update Threshold Is Weaker Than Install Block Threshold
The self-update flow says to overwrite the current learn skill if the new version scan passes with score at least 50, while the install flow blocks skills below 70. This could permit a lower-scoring update to replace the installer itself.
The lines directly describe fetching the latest version and overwriting the current skill when scan score is at least 50. The same file documents a stricter install block threshold elsewhere.
Medium
System reconnaissance
| Invalid score | "Score must be an integer between 1 and 5."
This section describes runtime installation, update, or feedback behavior that fetches remote content, writes skill files, or sends rating data. The behavior is purposeful, but it has supply-chain and privacy impact.
Medium
Opt-Out Rating and Feedback Telemetry
The skill instructs agents to rate installed skills by default, send ratings after a short confirmation window, and avoid ending a session with unrated skills. This sends platform and agent-generated comments to an external service unless disabled.
The cited section describes automatic rating, a 5-second default-send path, platform data, comments, and session-end rating behavior. It is disclosed, but it is still privacy-relevant external telemetry.
Capability review items (115)
These are real local capabilities that may be expected for this skill, so they require review but are not counted as confirmed malicious behavior.
High
Hidden file in home directory
1. Check if `.openclaw/` directory exists OR `~/.openclaw/workspace/` exists → **OpenClaw**
The skill detects or writes agent skill directories, which can alter future agent behavior. This is intended functionality, but writing remote skill content into hidden agent configuration paths is a real security-relevant filesystem action.
High
Hidden file in home directory
- Install path: `~/.openclaw/workspace/skills/<slug>.md`
The skill detects or writes agent skill directories, which can alter future agent behavior. This is intended functionality, but writing remote skill content into hidden agent configuration paths is a real security-relevant filesystem action.
Medium
Ruby/shell backtick execution
1. Use WebFetch to call: `https://agentskill.sh/api/agent/search?q=<URL-encoded query>&limit=5`
SKILL.md instructs the agent to contact agentskill.sh APIs for search, install, update, tracking, reports, or feedback. The domain matches the stated marketplace purpose, but it is real external network behavior.
Medium
Ruby/shell backtick execution
2. Use WebFetch to call: `https://agentskill.sh/api/agent/skills/<slug>/install?owner=<owner>`
SKILL.md instructs the agent to contact agentskill.sh APIs for search, install, update, tracking, reports, or feedback. The domain matches the stated marketplace purpose, but it is real external network behavior.
Medium
Ruby/shell backtick execution
1. Parse the slug from the URL path (last segment of `https://agentskill.sh/<slug>`)
SKILL.md instructs the agent to contact agentskill.sh APIs for search, install, update, tracking, reports, or feedback. The domain matches the stated marketplace purpose, but it is real external network behavior.
Medium
Ruby/shell backtick execution
2. Use WebFetch to call: `https://agentskill.sh/api/agent/skills/<slug>/install`
SKILL.md instructs the agent to contact agentskill.sh APIs for search, install, update, tracking, reports, or feedback. The domain matches the stated marketplace purpose, but it is real external network behavior.
Medium
Ruby/shell backtick execution
1. Use WebFetch to call: `https://agentskill.sh/api/agent/search?section=trending&limit=5`
SKILL.md instructs the agent to contact agentskill.sh APIs for search, install, update, tracking, reports, or feedback. The domain matches the stated marketplace purpose, but it is real external network behavior.
Medium
Ruby/shell backtick execution
3. Use WebFetch to POST to `https://agentskill.sh/api/skills/<slug>/agent-feedback` with JSON body:
SKILL.md instructs the agent to contact agentskill.sh APIs for search, install, update, tracking, reports, or feedback. The domain matches the stated marketplace purpose, but it is real external network behavior.
Medium
Ruby/shell backtick execution
2. Collect all slugs and call the batch version endpoint: `https://agentskill.sh/api/agent/skills/ve
SKILL.md instructs the agent to contact agentskill.sh APIs for search, install, update, tracking, reports, or feedback. The domain matches the stated marketplace purpose, but it is real external network behavior.
Medium
Ruby/shell backtick execution
1. Fetch skill content from `https://agentskill.sh/api/agent/skills/<slug>/install?platform=<platfor
SKILL.md instructs the agent to contact agentskill.sh APIs for search, install, update, tracking, reports, or feedback. The domain matches the stated marketplace purpose, but it is real external network behavior.
Medium
Ruby/shell backtick execution
```
This section describes runtime installation, update, or feedback behavior that fetches remote content, writes skill files, or sends rating data. The behavior is purposeful, but it has supply-chain and privacy impact.
Medium
Ruby/shell backtick execution
```
This section describes runtime installation, update, or feedback behavior that fetches remote content, writes skill files, or sends rating data. The behavior is purposeful, but it has supply-chain and privacy impact.
Medium
Ruby/shell backtick execution
```
This section describes runtime installation, update, or feedback behavior that fetches remote content, writes skill files, or sends rating data. The behavior is purposeful, but it has supply-chain and privacy impact.
Medium
Ruby/shell backtick execution
```
This section describes runtime installation, update, or feedback behavior that fetches remote content, writes skill files, or sends rating data. The behavior is purposeful, but it has supply-chain and privacy impact.
Medium
Ruby/shell backtick execution
```
This section describes runtime installation, update, or feedback behavior that fetches remote content, writes skill files, or sends rating data. The behavior is purposeful, but it has supply-chain and privacy impact.
Medium
Ruby/shell backtick execution
```
This section describes runtime installation, update, or feedback behavior that fetches remote content, writes skill files, or sends rating data. The behavior is purposeful, but it has supply-chain and privacy impact.
Medium
Ruby/shell backtick execution
9. Track the install — use WebFetch to POST to `https://agentskill.sh/api/skills/<slug>/install` wit
SKILL.md instructs the agent to contact agentskill.sh APIs for search, install, update, tracking, reports, or feedback. The domain matches the stated marketplace purpose, but it is real external network behavior.
Medium
Ruby/shell backtick execution
```json
This section describes runtime installation, update, or feedback behavior that fetches remote content, writes skill files, or sends rating data. The behavior is purposeful, but it has supply-chain and privacy impact.
Medium
Ruby/shell backtick execution
```
This section describes runtime installation, update, or feedback behavior that fetches remote content, writes skill files, or sends rating data. The behavior is purposeful, but it has supply-chain and privacy impact.
Medium
Ruby/shell backtick execution
```
This section describes runtime installation, update, or feedback behavior that fetches remote content, writes skill files, or sends rating data. The behavior is purposeful, but it has supply-chain and privacy impact.
Medium
Ruby/shell backtick execution
**Location:** `<install path>`
This section describes runtime installation, update, or feedback behavior that fetches remote content, writes skill files, or sends rating data. The behavior is purposeful, but it has supply-chain and privacy impact.
Medium
Ruby/shell backtick execution
Rate this skill later: `/learn feedback <slug> <1-5> [optional comment]`
This section describes runtime installation, update, or feedback behavior that fetches remote content, writes skill files, or sends rating data. The behavior is purposeful, but it has supply-chain and privacy impact.
Medium
Ruby/shell backtick execution
```
This section describes runtime installation, update, or feedback behavior that fetches remote content, writes skill files, or sends rating data. The behavior is purposeful, but it has supply-chain and privacy impact.
Medium
Ruby/shell backtick execution
Before executing any subcommand, check if this `/learn` skill itself is up to date.
This section describes runtime installation, update, or feedback behavior that fetches remote content, writes skill files, or sends rating data. The behavior is purposeful, but it has supply-chain and privacy impact.
Medium
Ruby/shell backtick execution
1. Read the current `/learn` skill file and extract the `contentSha` from the metadata header
This section describes runtime installation, update, or feedback behavior that fetches remote content, writes skill files, or sends rating data. The behavior is purposeful, but it has supply-chain and privacy impact.
Medium
Ruby/shell backtick execution
2. Use WebFetch to call: `https://agentskill.sh/api/agent/skills/learn/version`
SKILL.md instructs the agent to contact agentskill.sh APIs for search, install, update, tracking, reports, or feedback. The domain matches the stated marketplace purpose, but it is real external network behavior.
Medium
Ruby/shell backtick execution
3. Compare the local `contentSha` with the remote `contentSha`
This section describes runtime installation, update, or feedback behavior that fetches remote content, writes skill files, or sends rating data. The behavior is purposeful, but it has supply-chain and privacy impact.
Medium
Ruby/shell backtick execution
a. Fetch the latest version from `https://agentskill.sh/api/agent/skills/learn/install`
SKILL.md instructs the agent to contact agentskill.sh APIs for search, install, update, tracking, reports, or feedback. The domain matches the stated marketplace purpose, but it is real external network behavior.
Medium
Ruby/shell backtick execution
1. Check if `.openclaw/` directory exists OR `~/.openclaw/workspace/` exists → **OpenClaw**
This section describes runtime installation, update, or feedback behavior that fetches remote content, writes skill files, or sends rating data. The behavior is purposeful, but it has supply-chain and privacy impact.
Medium
Ruby/shell backtick execution
- Install path: `~/.openclaw/workspace/skills/<slug>.md`
This section describes runtime installation, update, or feedback behavior that fetches remote content, writes skill files, or sends rating data. The behavior is purposeful, but it has supply-chain and privacy impact.
Medium
Ruby/shell backtick execution
2. Check if `.claude/` directory exists in the project root → **Claude Code / Claude Desktop**
This section describes runtime installation, update, or feedback behavior that fetches remote content, writes skill files, or sends rating data. The behavior is purposeful, but it has supply-chain and privacy impact.
Medium
Ruby/shell backtick execution
- Install path: `.claude/skills/<slug>.md`
This section describes runtime installation, update, or feedback behavior that fetches remote content, writes skill files, or sends rating data. The behavior is purposeful, but it has supply-chain and privacy impact.
Medium
Ruby/shell backtick execution
3. Check if `.cursor/` directory exists → **Cursor**
This section describes runtime installation, update, or feedback behavior that fetches remote content, writes skill files, or sends rating data. The behavior is purposeful, but it has supply-chain and privacy impact.
Medium
Ruby/shell backtick execution
- Install path: `.cursor/skills/<slug>.md`
This section describes runtime installation, update, or feedback behavior that fetches remote content, writes skill files, or sends rating data. The behavior is purposeful, but it has supply-chain and privacy impact.
Medium
Ruby/shell backtick execution
4. Check if `.github/copilot/` directory exists → **GitHub Copilot**
This section describes runtime installation, update, or feedback behavior that fetches remote content, writes skill files, or sends rating data. The behavior is purposeful, but it has supply-chain and privacy impact.
Medium
Ruby/shell backtick execution
- Install path: `.github/copilot/skills/<slug>.md`
This section describes runtime installation, update, or feedback behavior that fetches remote content, writes skill files, or sends rating data. The behavior is purposeful, but it has supply-chain and privacy impact.
Medium
Ruby/shell backtick execution
5. Check if `.windsurf/` directory exists → **Windsurf**
This section describes runtime installation, update, or feedback behavior that fetches remote content, writes skill files, or sends rating data. The behavior is purposeful, but it has supply-chain and privacy impact.
Medium
Ruby/shell backtick execution
- Install path: `.windsurf/skills/<slug>.md`
This section describes runtime installation, update, or feedback behavior that fetches remote content, writes skill files, or sends rating data. The behavior is purposeful, but it has supply-chain and privacy impact.
Medium
Ruby/shell backtick execution
6. Check if `.cline/` directory exists → **Cline**
This section describes runtime installation, update, or feedback behavior that fetches remote content, writes skill files, or sends rating data. The behavior is purposeful, but it has supply-chain and privacy impact.
Medium
Ruby/shell backtick execution
- Install path: `.cline/skills/<slug>.md`
This section describes runtime installation, update, or feedback behavior that fetches remote content, writes skill files, or sends rating data. The behavior is purposeful, but it has supply-chain and privacy impact.
Medium
Ruby/shell backtick execution
7. Check if `.codex/` directory exists → **Codex**
This section describes runtime installation, update, or feedback behavior that fetches remote content, writes skill files, or sends rating data. The behavior is purposeful, but it has supply-chain and privacy impact.
Medium
Ruby/shell backtick execution
- Install path: `.codex/skills/<slug>.md`
This section describes runtime installation, update, or feedback behavior that fetches remote content, writes skill files, or sends rating data. The behavior is purposeful, but it has supply-chain and privacy impact.
Medium
Ruby/shell backtick execution
8. Check if `.opencode/` directory exists → **OpenCode**
This section describes runtime installation, update, or feedback behavior that fetches remote content, writes skill files, or sends rating data. The behavior is purposeful, but it has supply-chain and privacy impact.
Medium
Ruby/shell backtick execution
- Install path: `.opencode/skills/<slug>.md`
This section describes runtime installation, update, or feedback behavior that fetches remote content, writes skill files, or sends rating data. The behavior is purposeful, but it has supply-chain and privacy impact.
Medium
Ruby/shell backtick execution
9. Check if `.aider/` directory exists → **Aider**
This section describes runtime installation, update, or feedback behavior that fetches remote content, writes skill files, or sends rating data. The behavior is purposeful, but it has supply-chain and privacy impact.
Medium
Ruby/shell backtick execution
- Install path: `.aider/skills/<slug>.md`
This section describes runtime installation, update, or feedback behavior that fetches remote content, writes skill files, or sends rating data. The behavior is purposeful, but it has supply-chain and privacy impact.
Medium
Ruby/shell backtick execution
10. Check if `.gemini/` directory exists → **Gemini CLI**
This section describes runtime installation, update, or feedback behavior that fetches remote content, writes skill files, or sends rating data. The behavior is purposeful, but it has supply-chain and privacy impact.
Medium
Ruby/shell backtick execution
- Install path: `.gemini/skills/<slug>.md`
This section describes runtime installation, update, or feedback behavior that fetches remote content, writes skill files, or sends rating data. The behavior is purposeful, but it has supply-chain and privacy impact.
Medium
Ruby/shell backtick execution
11. Check if `.amp/` directory exists → **Amp**
This section describes runtime installation, update, or feedback behavior that fetches remote content, writes skill files, or sends rating data. The behavior is purposeful, but it has supply-chain and privacy impact.
Medium
Ruby/shell backtick execution
- Install path: `.amp/skills/<slug>.md`
This section describes runtime installation, update, or feedback behavior that fetches remote content, writes skill files, or sends rating data. The behavior is purposeful, but it has supply-chain and privacy impact.
Medium
Ruby/shell backtick execution
12. Check if `.goose/` directory exists → **Goose**
This section describes runtime installation, update, or feedback behavior that fetches remote content, writes skill files, or sends rating data. The behavior is purposeful, but it has supply-chain and privacy impact.
Medium
Ruby/shell backtick execution
- Install path: `.goose/skills/<slug>.md`
This section describes runtime installation, update, or feedback behavior that fetches remote content, writes skill files, or sends rating data. The behavior is purposeful, but it has supply-chain and privacy impact.
Medium
Ruby/shell backtick execution
13. Check if `.roo-code/` directory exists → **Roo Code**
This section describes runtime installation, update, or feedback behavior that fetches remote content, writes skill files, or sends rating data. The behavior is purposeful, but it has supply-chain and privacy impact.
Medium
Ruby/shell backtick execution
- Install path: `.roo-code/skills/<slug>.md`
This section describes runtime installation, update, or feedback behavior that fetches remote content, writes skill files, or sends rating data. The behavior is purposeful, but it has supply-chain and privacy impact.
Medium
Ruby/shell backtick execution
14. Check if `.trae/` directory exists → **Trae**
This section describes runtime installation, update, or feedback behavior that fetches remote content, writes skill files, or sends rating data. The behavior is purposeful, but it has supply-chain and privacy impact.
Medium
Ruby/shell backtick execution
- Install path: `.trae/skills/<slug>.md`
This section describes runtime installation, update, or feedback behavior that fetches remote content, writes skill files, or sends rating data. The behavior is purposeful, but it has supply-chain and privacy impact.
Medium
Ruby/shell backtick execution
| `.openclaw/` | `openclaw` |
This section describes runtime installation, update, or feedback behavior that fetches remote content, writes skill files, or sends rating data. The behavior is purposeful, but it has supply-chain and privacy impact.
Medium
Ruby/shell backtick execution
| `.claude/` | `claude-code` |
This section describes runtime installation, update, or feedback behavior that fetches remote content, writes skill files, or sends rating data. The behavior is purposeful, but it has supply-chain and privacy impact.
Medium
Ruby/shell backtick execution
| `.cursor/` | `cursor` |
This section describes runtime installation, update, or feedback behavior that fetches remote content, writes skill files, or sends rating data. The behavior is purposeful, but it has supply-chain and privacy impact.
Medium
Ruby/shell backtick execution
| `.github/copilot/` | `copilot` |
This section describes runtime installation, update, or feedback behavior that fetches remote content, writes skill files, or sends rating data. The behavior is purposeful, but it has supply-chain and privacy impact.
Medium
Ruby/shell backtick execution
| `.windsurf/` | `windsurf` |
This section describes runtime installation, update, or feedback behavior that fetches remote content, writes skill files, or sends rating data. The behavior is purposeful, but it has supply-chain and privacy impact.
Medium
Ruby/shell backtick execution
| `.cline/` | `cline` |
This section describes runtime installation, update, or feedback behavior that fetches remote content, writes skill files, or sends rating data. The behavior is purposeful, but it has supply-chain and privacy impact.
Medium
Ruby/shell backtick execution
| `.codex/` | `codex` |
This section describes runtime installation, update, or feedback behavior that fetches remote content, writes skill files, or sends rating data. The behavior is purposeful, but it has supply-chain and privacy impact.
Medium
Ruby/shell backtick execution
| `.opencode/` | `opencode` |
This section describes runtime installation, update, or feedback behavior that fetches remote content, writes skill files, or sends rating data. The behavior is purposeful, but it has supply-chain and privacy impact.
Medium
Ruby/shell backtick execution
| `.aider/` | `aider` |
This section describes runtime installation, update, or feedback behavior that fetches remote content, writes skill files, or sends rating data. The behavior is purposeful, but it has supply-chain and privacy impact.
Medium
Ruby/shell backtick execution
| `.gemini/` | `gemini-cli` |
This section describes runtime installation, update, or feedback behavior that fetches remote content, writes skill files, or sends rating data. The behavior is purposeful, but it has supply-chain and privacy impact.
Medium
Ruby/shell backtick execution
| `.amp/` | `amp` |
This section describes runtime installation, update, or feedback behavior that fetches remote content, writes skill files, or sends rating data. The behavior is purposeful, but it has supply-chain and privacy impact.
Medium
Ruby/shell backtick execution
| `.goose/` | `goose` |
This section describes runtime installation, update, or feedback behavior that fetches remote content, writes skill files, or sends rating data. The behavior is purposeful, but it has supply-chain and privacy impact.
Medium
Ruby/shell backtick execution
| `.roo-code/` | `roo-code` |
This section describes runtime installation, update, or feedback behavior that fetches remote content, writes skill files, or sends rating data. The behavior is purposeful, but it has supply-chain and privacy impact.
Medium
Ruby/shell backtick execution
| `.trae/` | `trae` |
This section describes runtime installation, update, or feedback behavior that fetches remote content, writes skill files, or sends rating data. The behavior is purposeful, but it has supply-chain and privacy impact.
Medium
Ruby/shell backtick execution
When creating the skill directory, create it if it doesn't exist (e.g., `mkdir -p .claude/skills/`).
This section describes runtime installation, update, or feedback behavior that fetches remote content, writes skill files, or sends rating data. The behavior is purposeful, but it has supply-chain and privacy impact.
Medium
Ruby/shell backtick execution
```
This section describes runtime installation, update, or feedback behavior that fetches remote content, writes skill files, or sends rating data. The behavior is purposeful, but it has supply-chain and privacy impact.
Medium
Ruby/shell backtick execution
Send rating? (Y/n) — disable auto-rating: `/learn config autorating off`
This section describes runtime installation, update, or feedback behavior that fetches remote content, writes skill files, or sends rating data. The behavior is purposeful, but it has supply-chain and privacy impact.
Medium
Ruby/shell backtick execution
```
This section describes runtime installation, update, or feedback behavior that fetches remote content, writes skill files, or sends rating data. The behavior is purposeful, but it has supply-chain and privacy impact.
Medium
Ruby/shell backtick execution
```json
This section describes runtime installation, update, or feedback behavior that fetches remote content, writes skill files, or sends rating data. The behavior is purposeful, but it has supply-chain and privacy impact.
Medium
Ruby/shell backtick execution
```
This section describes runtime installation, update, or feedback behavior that fetches remote content, writes skill files, or sends rating data. The behavior is purposeful, but it has supply-chain and privacy impact.
Medium
Ruby/shell backtick execution
4. **User can override anytime**: `/learn feedback <slug> <score> [comment]`
This section describes runtime installation, update, or feedback behavior that fetches remote content, writes skill files, or sends rating data. The behavior is purposeful, but it has supply-chain and privacy impact.
Medium
Ruby/shell backtick execution
```
This section describes runtime installation, update, or feedback behavior that fetches remote content, writes skill files, or sends rating data. The behavior is purposeful, but it has supply-chain and privacy impact.
Medium
Ruby/shell backtick execution
```
This section describes runtime installation, update, or feedback behavior that fetches remote content, writes skill files, or sends rating data. The behavior is purposeful, but it has supply-chain and privacy impact.
Medium
Ruby/shell backtick execution
Re-enable with: `/learn config autorating on`
This section describes runtime installation, update, or feedback behavior that fetches remote content, writes skill files, or sends rating data. The behavior is purposeful, but it has supply-chain and privacy impact.
Medium
Ruby/shell backtick execution
- `/learn feedback <slug> <new-score> [comment]`
This section describes runtime installation, update, or feedback behavior that fetches remote content, writes skill files, or sends rating data. The behavior is purposeful, but it has supply-chain and privacy impact.
Medium
Ruby/shell backtick execution
```
This section describes runtime installation, update, or feedback behavior that fetches remote content, writes skill files, or sends rating data. The behavior is purposeful, but it has supply-chain and privacy impact.
Medium
Ruby/shell backtick execution
*Override any rating: `/learn feedback <slug> <score> [comment]`*
This section describes runtime installation, update, or feedback behavior that fetches remote content, writes skill files, or sends rating data. The behavior is purposeful, but it has supply-chain and privacy impact.
Medium
Ruby/shell backtick execution
```
This section describes runtime installation, update, or feedback behavior that fetches remote content, writes skill files, or sends rating data. The behavior is purposeful, but it has supply-chain and privacy impact.
Medium
Ruby/shell backtick execution
All endpoints are on `https://agentskill.sh`.
SKILL.md instructs the agent to contact agentskill.sh APIs for search, install, update, tracking, reports, or feedback. The domain matches the stated marketplace purpose, but it is real external network behavior.
Medium
Ruby/shell backtick execution
| `/api/agent/search?q=<query>&limit=5` | GET | Search skills
This section describes runtime installation, update, or feedback behavior that fetches remote content, writes skill files, or sends rating data. The behavior is purposeful, but it has supply-chain and privacy impact.
Medium
Ruby/shell backtick execution
| `/api/agent/skills/<slug>/install` | GET | Get skill content for installation
This section describes runtime installation, update, or feedback behavior that fetches remote content, writes skill files, or sends rating data. The behavior is purposeful, but it has supply-chain and privacy impact.
Medium
Ruby/shell backtick execution
| `/api/agent/skills/<slug>/version` | GET | Get content SHA for version check
This section describes runtime installation, update, or feedback behavior that fetches remote content, writes skill files, or sends rating data. The behavior is purposeful, but it has supply-chain and privacy impact.
Medium
Ruby/shell backtick execution
| `/api/agent/skills/version?slugs=<csv>` | GET | Batch version check
This section describes runtime installation, update, or feedback behavior that fetches remote content, writes skill files, or sends rating data. The behavior is purposeful, but it has supply-chain and privacy impact.
Medium
Ruby/shell backtick execution
| `/api/skills/<slug>/install` | POST | Track install event
SKILL.md instructs the agent to contact agentskill.sh APIs for search, install, update, tracking, reports, or feedback. The domain matches the stated marketplace purpose, but it is real external network behavior.
Medium
Ruby/shell backtick execution
| `/api/skills/<slug>/agent-feedback` | POST | Submit score and comment (include `autoRated: t
SKILL.md instructs the agent to contact agentskill.sh APIs for search, install, update, tracking, reports, or feedback. The domain matches the stated marketplace purpose, but it is real external network behavior.
Medium
Hidden file access
1. Check if `.openclaw/` directory exists OR `~/.openclaw/workspace/` exists → **OpenClaw**
The skill detects or writes agent skill directories, which can alter future agent behavior. This is intended functionality, but writing remote skill content into hidden agent configuration paths is a real security-relevant filesystem action.
Medium
Hidden file access
- Install path: `~/.openclaw/workspace/skills/<slug>.md`
The skill detects or writes agent skill directories, which can alter future agent behavior. This is intended functionality, but writing remote skill content into hidden agent configuration paths is a real security-relevant filesystem action.
Low
Python HTTP libraries
- Manual: check for `os.system`, `subprocess(shell=True)`, `exec`, `eval`, `pickle.loads`, `requests
SKILL.md instructs the agent to contact agentskill.sh APIs for search, install, update, tracking, reports, or feedback. The domain matches the stated marketplace purpose, but it is real external network behavior.
Low
Python HTTP libraries
| Rate limited (429) | "Too many requests. Please wait a moment and try again."
SKILL.md instructs the agent to contact agentskill.sh APIs for search, install, update, tracking, reports, or feedback. The domain matches the stated marketplace purpose, but it is real external network behavior.
Low
Hardcoded URL
Discover, install, and manage AI agent skills from [agentskill.sh](https://agentskill.sh). This skil
SKILL.md instructs the agent to contact agentskill.sh APIs for search, install, update, tracking, reports, or feedback. The domain matches the stated marketplace purpose, but it is real external network behavior.
Low
Hardcoded URL
1. Use WebFetch to call: `https://agentskill.sh/api/agent/search?q=<URL-encoded query>&limit=5`
SKILL.md instructs the agent to contact agentskill.sh APIs for search, install, update, tracking, reports, or feedback. The domain matches the stated marketplace purpose, but it is real external network behavior.
Low
Hardcoded URL
If no results are found, say: "No skills found for '<query>'. Try different keywords or browse at ht
SKILL.md instructs the agent to contact agentskill.sh APIs for search, install, update, tracking, reports, or feedback. The domain matches the stated marketplace purpose, but it is real external network behavior.
Low
Hardcoded URL
2. Use WebFetch to call: `https://agentskill.sh/api/agent/skills/<slug>/install?owner=<owner>`
SKILL.md instructs the agent to contact agentskill.sh APIs for search, install, update, tracking, reports, or feedback. The domain matches the stated marketplace purpose, but it is real external network behavior.
Low
Hardcoded URL
4. If not found, say: "Skill @<owner>/<slug> not found. Check the name at https://agentskill.sh"
SKILL.md instructs the agent to contact agentskill.sh APIs for search, install, update, tracking, reports, or feedback. The domain matches the stated marketplace purpose, but it is real external network behavior.
Low
Hardcoded URL
1. Parse the slug from the URL path (last segment of `https://agentskill.sh/<slug>`)
SKILL.md instructs the agent to contact agentskill.sh APIs for search, install, update, tracking, reports, or feedback. The domain matches the stated marketplace purpose, but it is real external network behavior.
Low
Hardcoded URL
2. Use WebFetch to call: `https://agentskill.sh/api/agent/skills/<slug>/install`
SKILL.md instructs the agent to contact agentskill.sh APIs for search, install, update, tracking, reports, or feedback. The domain matches the stated marketplace purpose, but it is real external network behavior.
Low
Hardcoded URL
1. Use WebFetch to call: `https://agentskill.sh/api/agent/search?section=trending&limit=5`
SKILL.md instructs the agent to contact agentskill.sh APIs for search, install, update, tracking, reports, or feedback. The domain matches the stated marketplace purpose, but it is real external network behavior.
Low
Hardcoded URL
3. Use WebFetch to POST to `https://agentskill.sh/api/skills/<slug>/agent-feedback` with JSON body:
SKILL.md instructs the agent to contact agentskill.sh APIs for search, install, update, tracking, reports, or feedback. The domain matches the stated marketplace purpose, but it is real external network behavior.
Low
Hardcoded URL
2. Collect all slugs and call the batch version endpoint: `https://agentskill.sh/api/agent/skills/ve
SKILL.md instructs the agent to contact agentskill.sh APIs for search, install, update, tracking, reports, or feedback. The domain matches the stated marketplace purpose, but it is real external network behavior.
Low
Hardcoded URL
1. Fetch skill content from `https://agentskill.sh/api/agent/skills/<slug>/install?platform=<platfor
SKILL.md instructs the agent to contact agentskill.sh APIs for search, install, update, tracking, reports, or feedback. The domain matches the stated marketplace purpose, but it is real external network behavior.
Low
Hardcoded URL
# source: https://agentskill.sh/<slug>
SKILL.md instructs the agent to contact agentskill.sh APIs for search, install, update, tracking, reports, or feedback. The domain matches the stated marketplace purpose, but it is real external network behavior.
Low
Hardcoded URL
9. Track the install — use WebFetch to POST to `https://agentskill.sh/api/skills/<slug>/install` wit
SKILL.md instructs the agent to contact agentskill.sh APIs for search, install, update, tracking, reports, or feedback. The domain matches the stated marketplace purpose, but it is real external network behavior.
Low
Hardcoded URL
POST https://agentskill.sh/api/agent/security-reports
SKILL.md instructs the agent to contact agentskill.sh APIs for search, install, update, tracking, reports, or feedback. The domain matches the stated marketplace purpose, but it is real external network behavior.
Low
Hardcoded URL
2. Use WebFetch to call: `https://agentskill.sh/api/agent/skills/learn/version`
SKILL.md instructs the agent to contact agentskill.sh APIs for search, install, update, tracking, reports, or feedback. The domain matches the stated marketplace purpose, but it is real external network behavior.
Low
Hardcoded URL
a. Fetch the latest version from `https://agentskill.sh/api/agent/skills/learn/install`
SKILL.md instructs the agent to contact agentskill.sh APIs for search, install, update, tracking, reports, or feedback. The domain matches the stated marketplace purpose, but it is real external network behavior.
Low
Hardcoded URL
| API unreachable / timeout | "Could not reach agentskill.sh. Check your connection or try again lat
SKILL.md instructs the agent to contact agentskill.sh APIs for search, install, update, tracking, reports, or feedback. The domain matches the stated marketplace purpose, but it is real external network behavior.
Low
Hardcoded URL
| No search results | "No skills found for '<query>'. Try different keywords or browse at ht
SKILL.md instructs the agent to contact agentskill.sh APIs for search, install, update, tracking, reports, or feedback. The domain matches the stated marketplace purpose, but it is real external network behavior.
Low
Hardcoded URL
| Skill not found (404) | "Skill '<slug>' not found. It may have been removed. Browse available
SKILL.md instructs the agent to contact agentskill.sh APIs for search, install, update, tracking, reports, or feedback. The domain matches the stated marketplace purpose, but it is real external network behavior.
Low
Hardcoded URL
All endpoints are on `https://agentskill.sh`.
SKILL.md instructs the agent to contact agentskill.sh APIs for search, install, update, tracking, reports, or feedback. The domain matches the stated marketplace purpose, but it is real external network behavior.
Risk Factors
🌐 Network access (30)
README.md:40 README.md:52 README.md:55 README.md:130 references/SECURITY.md:417 references/SECURITY.md:419 references/SECURITY.md:544 references/SECURITY.md:300 SKILL.md:451 SKILL.md:771 SKILL.md:11 SKILL.md:40 SKILL.md:68 SKILL.md:77 SKILL.md:79 SKILL.md:87 SKILL.md:88 SKILL.md:121 SKILL.md:133 SKILL.md:179 SKILL.md:256 SKILL.md:325 SKILL.md:331 SKILL.md:501 SKILL.md:561 SKILL.md:565 SKILL.md:768 SKILL.md:769 SKILL.md:770 SKILL.md:781
📁 Filesystem access (45)
README.md:52 README.md:55 README.md:140 README.md:141 README.md:143 README.md:144 README.md:145 README.md:52 README.md:55 README.md:140 README.md:141 README.md:143 README.md:144 README.md:145 references/SECURITY.md:112 references/SECURITY.md:117 references/SECURITY.md:118 references/SECURITY.md:119 references/SECURITY.md:120 references/SECURITY.md:130 references/SECURITY.md:138 references/SECURITY.md:139 references/SECURITY.md:218 references/SECURITY.md:418 references/SECURITY.md:112 references/SECURITY.md:117 references/SECURITY.md:118 references/SECURITY.md:119 references/SECURITY.md:120 references/SECURITY.md:130 references/SECURITY.md:138 references/SECURITY.md:139 references/SECURITY.md:218 references/SECURITY.md:418 references/SECURITY.md:163 SKILL.md:410 SKILL.md:440 SKILL.md:582 SKILL.md:583 SKILL.md:410 SKILL.md:417 SKILL.md:440 SKILL.md:582 SKILL.md:583 SKILL.md:412
⚡ Contains scripts (3)
⚙️ External commands (50)
references/SECURITY.md:412 references/SECURITY.md:413 references/SECURITY.md:411 references/SECURITY.md:630-635 references/SECURITY.md:149 SKILL.md:13 SKILL.md:22 SKILL.md:23 SKILL.md:24 SKILL.md:25 SKILL.md:32-34 SKILL.md:34-36 SKILL.md:36-40 SKILL.md:40-44 SKILL.md:44-57 SKILL.md:57-59 SKILL.md:59-70 SKILL.md:70-72 SKILL.md:72-76 SKILL.md:76-77 SKILL.md:77-81 SKILL.md:81-83 SKILL.md:83-87 SKILL.md:87-88 SKILL.md:88-91 SKILL.md:91-93 SKILL.md:93-98 SKILL.md:98-99 SKILL.md:99 SKILL.md:100 SKILL.md:101-103 SKILL.md:103 SKILL.md:104-105 SKILL.md:105-109 SKILL.md:109-113 SKILL.md:113-117 SKILL.md:117-121 SKILL.md:121-125 SKILL.md:125-131 SKILL.md:131 SKILL.md:133-134 SKILL.md:134-141 SKILL.md:141-144 SKILL.md:144-151 SKILL.md:151-153 SKILL.md:153-158 SKILL.md:158-159 SKILL.md:159 SKILL.md:162-171 SKILL.md:171-172
🔑 Env variables (1)
Detected Patterns
System reconnaissance[HEURISTIC] DANGEROUS COMBINATION: Code execution + Network + Credential access[HEURISTIC] DANGEROUS COMBINATION: Network + Credentials + Evasion techniques
Audited by: claude View Audit History →
Share & cite this report
Share the versioned assessment report, neutral badge, embed card, and citations. Skillstore reports evidence without deciding whether this Skill is safe.
Copy report link
https://skillstore.io/skills/agentskill-sh-learn/audits/7?utm_source=security_passport&utm_medium=share&utm_campaign=versioned_reportMarkdown badge
[](https://skillstore.io/skills/agentskill-sh-learn?utm_source=security_passport_badge)HTML badge
<a href="https://skillstore.io/skills/agentskill-sh-learn?utm_source=security_passport_badge"><img src="https://skillstore.io/badges/skills/agentskill-sh-learn/security.svg" alt="Skillstore security assessment" loading="lazy"></a>Embed card
<iframe src="https://skillstore.io/embed/skills/agentskill-sh-learn.html" title="Skillstore Security Assessment" sandbox="allow-popups allow-popups-to-escape-sandbox" loading="lazy" referrerpolicy="no-referrer" width="420" height="180"></iframe>Academic citations (APA · BibTeX · CFF)
APA citation
agentskill-sh. (2026). learn security audit report (audit version 7) [Author version 2.0]. Skillstore. https://skillstore.io/skills/agentskill-sh-learn/audits/7BibTeX citation
@techreport{agentskill-sh-agentskill-sh-learn-2026,
author = {agentskill-sh},
title = {learn security audit report (audit version 7)},
institution = {Skillstore},
year = {2026},
number = {7},
url = {https://skillstore.io/skills/agentskill-sh-learn/audits/7},
note = {Author version 2.0}
}CITATION.cff
cff-version: 1.2.0
message: "If you use this Skill, cite its author and this versioned security audit report."
title: "learn security audit report (audit version 7)"
version: "2.0"
type: report
authors:
- name: "agentskill-sh"
date-released: "2026-07-09"
url: "https://skillstore.io/skills/agentskill-sh-learn/audits/7"
identifiers:
- type: other
value: "skillstore:agentskill-sh-learn:audit:7"
description: "Skillstore immutable audit report identifier"
Compare variants
2 installable variantsEach author remains a separate installable skill. The recommended variant is ranked by Skillstore evidence.
Why this variant is first
Highest Skillstore Score
Author / source Skillstore Score Evidence Confidence Skillstore usage Updated
0xrdan Recommended
0xrdan-learn
Skillstore Score 70
Evidence Confidence High
Skillstore usage 27
Updated
2026-08-21
agentskill-sh Current
agentskill-sh-learn
Skillstore Score 38
Evidence Confidence Medium
Skillstore usage 75
Updated
2026-08-21
Skillstore Score
Why this score Evidence Confidence: Medium 55
Architecture
85
Maintainability
85
Content
69
Community
74
Spec Compliance
What You Can Build
Find a missing capability
Search for a skill that matches a current task, such as SEO, payments, documentation, or framework guidance.
Manage installed skills
List installed skills, check for updates, remove unused skills, and keep local metadata current.
Review skill safety before install
Scan a local or remote skill for risky patterns before allowing it to influence agent behavior.
Try These Prompts
Search for a skill
/learn frontend react components
Install a known skill
/learn @owner/skill-slug
Audit a local skill
/learn scan ./SKILL.md
Update managed skills
/learn update
Best Practices
- Review the preview, source, and security score before installing any skill.
- Use scan mode for local or third-party skills before adding them to an agent workspace.
- Disable automatic rating if your team does not want feedback sent to an external service.
Avoid
- Do not install low-score skills just because they match the task keywords.
- Do not treat pattern-based scans as a complete substitute for manual review of untrusted instructions.
- Do not allow remote skill updates in sensitive workspaces without reviewing changed content.
Frequently Asked Questions
What does this skill do?
It searches, previews, installs, updates, removes, scans, and rates AI agent skills from agentskill.sh.
Does it work with Claude Code?
Yes. The skill declares support for Claude, Codex, and Claude Code.
Does it install code automatically?
It can write skill files after a preview, security scan, and user confirmation step described in the instructions.
Can the security scan prove a skill is safe?
No. It detects known risky patterns, but users should still review untrusted skill content.
What data can it send externally?
It contacts agentskill.sh for search, install, update, install tracking, feedback, and security report workflows.
When should teams avoid it?
Avoid it in restricted environments where remote instructions, telemetry, or workspace skill writes are not allowed.
Developer Details
Author
agentskill-shLicense
MIT
Author version
v2.0
Skillstore revision
r1
Version notice
The author-declared version is not valid SemVer.
Ref
1ffa7643651792ccb4bd3b15d924d2c97edff755
Maintenance freshness
7/18/2026
Usage
70 downloads · 162 views
File structure