技能 learn

📦

learn

Name: learn
Author: agentskill-sh

v2.0 内容修订 r1 严重 🌐 网络访问📁 文件系统访问⚡ 包含脚本⚙️ 外部命令🔑 环境变量

在对话中途安装智能体技能

智能体经常需要在会话开始时未加载的专用指令。此技能让 Claude、Codex 和 Claude Code 能够从 agentskill.sh 搜索、预览、扫描、安装、更新、移除和评价技能。

支持: Claude Codex Code(CC)

⚠️ 38 差

请勿自动安装此 Skill。

权威策略要求在执行任何安装操作前由操作人员审查。

使用我的智能体安装

将此请求复制给你的智能体，其中包含权威 Skill 页面和清单。

智能体请求

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.

你的智能体仍应展示其计划，并按安全策略请求必要确认。

Agent 可读资源

当 AI Agent、爬虫或脚本需要干净上下文，而不是读取完整页面时，请使用这些链接。

Markdown 详情 GET /skills/agentskill-sh-learn.md 已签名 manifest GET /api/skills/agentskill-sh-learn/manifest 已签名 lockfile GET /api/skills/agentskill-sh-learn/lockfile

测试它

正在使用“learn”。 /learn documentation

预期结果:

一个按排名展示匹配技能的表格，包含作者、安装次数、安全评分、简短描述，以及一个交互式安装选择。

正在使用“learn”。 /learn scan ./SKILL.md

预期结果:

一份安全报告，列出评分、检测到的问题、网络端点、文件访问、shell 命令，以及允许或阻止的建议。

正在使用“learn”。 /learn update

预期结果:

一份已安装技能摘要，包括更新状态、安全重新扫描结果，以及应用更新前的确认提示。

安全审计

严重

v7 • 2026/7/9 打开版本化报告

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.

已扫描文件

1,630

分析行数

115

复核项

已忽略误报

已确认安全问题 (8)

严重

multiple:1

[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.

严重

multiple:1

[HEURISTIC] DANGEROUS COMBINATION: Network + Credentials + Evasion techniques

This combination suggests data exfiltration with anti-detection

高

multiple:1

[HEURISTIC] SUSPICIOUS COMBINATION: Code execution + Persistence mechanism

This combination is common in malware that maintains access

高

multiple:1

[HEURISTIC] SUSPICIOUS COMBINATION: Filesystem + Credentials + Network

This combination could indicate credential harvesting and exfiltration

高

SKILL.md:256-331

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.

高

SKILL.md:560-568

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.

中

SKILL.md:772

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.

中

SKILL.md:634-760

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.

能力复核项 (115)

这些是真实的本地能力，对此技能可能是预期行为，因此需要复核，但不会按已确认恶意行为计分。

高

SKILL.md:582

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.

高

SKILL.md:583

Hidden file in home directory

- Install path: `~/.openclaw/workspace/skills/<slug>.md`

中

SKILL.md:40-44

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.

中

SKILL.md:77-81

Ruby/shell backtick execution

2. Use WebFetch to call: `https://agentskill.sh/api/agent/skills/<slug>/install?owner=<owner>`

中

SKILL.md:87-88

Ruby/shell backtick execution

1. Parse the slug from the URL path (last segment of `https://agentskill.sh/<slug>`)

中

SKILL.md:88-91

Ruby/shell backtick execution

2. Use WebFetch to call: `https://agentskill.sh/api/agent/skills/<slug>/install`

中

SKILL.md:121-125

Ruby/shell backtick execution

1. Use WebFetch to call: `https://agentskill.sh/api/agent/search?section=trending&limit=5`

中

SKILL.md:133-134

Ruby/shell backtick execution

3. Use WebFetch to POST to `https://agentskill.sh/api/skills/<slug>/agent-feedback` with JSON body:

中

SKILL.md:179-180

Ruby/shell backtick execution

2. Collect all slugs and call the batch version endpoint: `https://agentskill.sh/api/agent/skills/ve

中

SKILL.md:256-270

Ruby/shell backtick execution

1. Fetch skill content from `https://agentskill.sh/api/agent/skills/<slug>/install?platform=<platfor

中

SKILL.md:270-280

Ruby/shell backtick execution

```

中

SKILL.md:280-284

Ruby/shell backtick execution

```

中

SKILL.md:284-296

Ruby/shell backtick execution

```

中

SKILL.md:296-318

Ruby/shell backtick execution

```

中

SKILL.md:318-329

Ruby/shell backtick execution

```

中

SKILL.md:329-331

Ruby/shell backtick execution

```

中

SKILL.md:331-333

Ruby/shell backtick execution

9. Track the install — use WebFetch to POST to `https://agentskill.sh/api/skills/<slug>/install` wit

中

SKILL.md:333-338

Ruby/shell backtick execution

```json

中

SKILL.md:338-344

Ruby/shell backtick execution

```

中

SKILL.md:344-347

Ruby/shell backtick execution

```

中

SKILL.md:347-354

Ruby/shell backtick execution

**Location:** `<install path>`

中

SKILL.md:354-355

Ruby/shell backtick execution

Rate this skill later: `/learn feedback <slug> <1-5> [optional comment]`

中

SKILL.md:355-371

Ruby/shell backtick execution

```

中

SKILL.md:556-560

Ruby/shell backtick execution

Before executing any subcommand, check if this `/learn` skill itself is up to date.

中

SKILL.md:560

Ruby/shell backtick execution

1. Read the current `/learn` skill file and extract the `contentSha` from the metadata header

中

SKILL.md:561-562

Ruby/shell backtick execution

2. Use WebFetch to call: `https://agentskill.sh/api/agent/skills/learn/version`

中

SKILL.md:562

Ruby/shell backtick execution

3. Compare the local `contentSha` with the remote `contentSha`

中

SKILL.md:565-582

Ruby/shell backtick execution

a. Fetch the latest version from `https://agentskill.sh/api/agent/skills/learn/install`

中

SKILL.md:582

Ruby/shell backtick execution

1. Check if `.openclaw/` directory exists OR `~/.openclaw/workspace/` exists → **OpenClaw**

中

SKILL.md:583-584

Ruby/shell backtick execution

- Install path: `~/.openclaw/workspace/skills/<slug>.md`

中

SKILL.md:584-585

Ruby/shell backtick execution

2. Check if `.claude/` directory exists in the project root → **Claude Code / Claude Desktop**

中

SKILL.md:585-586

Ruby/shell backtick execution

- Install path: `.claude/skills/<slug>.md`

中

SKILL.md:586-587

Ruby/shell backtick execution

3. Check if `.cursor/` directory exists → **Cursor**

中

SKILL.md:587-588

Ruby/shell backtick execution

- Install path: `.cursor/skills/<slug>.md`

中

SKILL.md:588-589

Ruby/shell backtick execution

4. Check if `.github/copilot/` directory exists → **GitHub Copilot**

中

SKILL.md:589-590

Ruby/shell backtick execution

- Install path: `.github/copilot/skills/<slug>.md`

中

SKILL.md:590-591

Ruby/shell backtick execution

5. Check if `.windsurf/` directory exists → **Windsurf**

中

SKILL.md:591-592

Ruby/shell backtick execution

- Install path: `.windsurf/skills/<slug>.md`

中

SKILL.md:592-593

Ruby/shell backtick execution

6. Check if `.cline/` directory exists → **Cline**

中

SKILL.md:593-594

Ruby/shell backtick execution

- Install path: `.cline/skills/<slug>.md`

中

SKILL.md:594-595

Ruby/shell backtick execution

7. Check if `.codex/` directory exists → **Codex**

中

SKILL.md:595-596

Ruby/shell backtick execution

- Install path: `.codex/skills/<slug>.md`

中

SKILL.md:596-597

Ruby/shell backtick execution

8. Check if `.opencode/` directory exists → **OpenCode**

中

SKILL.md:597-598

Ruby/shell backtick execution

- Install path: `.opencode/skills/<slug>.md`

中

SKILL.md:598-599

Ruby/shell backtick execution

9. Check if `.aider/` directory exists → **Aider**

中

SKILL.md:599-600

Ruby/shell backtick execution

- Install path: `.aider/skills/<slug>.md`

中

SKILL.md:600-601

Ruby/shell backtick execution

10. Check if `.gemini/` directory exists → **Gemini CLI**

中

SKILL.md:601-602

Ruby/shell backtick execution

- Install path: `.gemini/skills/<slug>.md`

中

SKILL.md:602-603

Ruby/shell backtick execution

11. Check if `.amp/` directory exists → **Amp**

中

SKILL.md:603-604

Ruby/shell backtick execution

- Install path: `.amp/skills/<slug>.md`

中

SKILL.md:604-605

Ruby/shell backtick execution

12. Check if `.goose/` directory exists → **Goose**

中

SKILL.md:605-606

Ruby/shell backtick execution

- Install path: `.goose/skills/<slug>.md`

中

SKILL.md:606-607

Ruby/shell backtick execution

13. Check if `.roo-code/` directory exists → **Roo Code**

中

SKILL.md:607-608

Ruby/shell backtick execution

- Install path: `.roo-code/skills/<slug>.md`

中

SKILL.md:608-609

Ruby/shell backtick execution

14. Check if `.trae/` directory exists → **Trae**

中

SKILL.md:609-615

Ruby/shell backtick execution

- Install path: `.trae/skills/<slug>.md`

中

SKILL.md:615

Ruby/shell backtick execution

| `.openclaw/` | `openclaw` |

中

SKILL.md:616

Ruby/shell backtick execution

| `.claude/` | `claude-code` |

中

SKILL.md:617

Ruby/shell backtick execution

| `.cursor/` | `cursor` |

中

SKILL.md:618

Ruby/shell backtick execution

| `.github/copilot/` | `copilot` |

中

SKILL.md:619

Ruby/shell backtick execution

| `.windsurf/` | `windsurf` |

中

SKILL.md:620

Ruby/shell backtick execution

| `.cline/` | `cline` |

中

SKILL.md:621

Ruby/shell backtick execution

| `.codex/` | `codex` |

中

SKILL.md:622

Ruby/shell backtick execution

| `.opencode/` | `opencode` |

中

SKILL.md:623

Ruby/shell backtick execution

| `.aider/` | `aider` |

中

SKILL.md:624

Ruby/shell backtick execution

| `.gemini/` | `gemini-cli` |

中

SKILL.md:625

Ruby/shell backtick execution

| `.amp/` | `amp` |

中

SKILL.md:626

Ruby/shell backtick execution

| `.goose/` | `goose` |

中

SKILL.md:627

Ruby/shell backtick execution

| `.roo-code/` | `roo-code` |

中

SKILL.md:628

Ruby/shell backtick execution

| `.trae/` | `trae` |

中

SKILL.md:630-660

Ruby/shell backtick execution

When creating the skill directory, create it if it doesn't exist (e.g., `mkdir -p .claude/skills/`).

中

SKILL.md:660-663

Ruby/shell backtick execution

```

中

SKILL.md:663-664

Ruby/shell backtick execution

Send rating? (Y/n) — disable auto-rating: `/learn config autorating off`

中

SKILL.md:664-666

Ruby/shell backtick execution

```

中

SKILL.md:666-674

Ruby/shell backtick execution

```json

中

SKILL.md:674-675

Ruby/shell backtick execution

```

中

SKILL.md:675-686

Ruby/shell backtick execution

4. **User can override anytime**: `/learn feedback <slug> <score> [comment]`

中

SKILL.md:686-688

Ruby/shell backtick execution

```

中

SKILL.md:688-690

Ruby/shell backtick execution

```

中

SKILL.md:690-706

Ruby/shell backtick execution

Re-enable with: `/learn config autorating on`

中

SKILL.md:706-751

Ruby/shell backtick execution

- `/learn feedback <slug> <new-score> [comment]`

中

SKILL.md:751-757

Ruby/shell backtick execution

```

中

SKILL.md:757-758

Ruby/shell backtick execution

*Override any rating: `/learn feedback <slug> <score> [comment]`*

中

SKILL.md:758-781

Ruby/shell backtick execution

```

中

SKILL.md:781-785

Ruby/shell backtick execution

All endpoints are on `https://agentskill.sh`.

中

SKILL.md:785-786

Ruby/shell backtick execution

| `/api/agent/search?q=<query>&limit=5` | GET | Search skills

中

SKILL.md:786-787

Ruby/shell backtick execution

| `/api/agent/skills/<slug>/install` | GET | Get skill content for installation

中

SKILL.md:787-788

Ruby/shell backtick execution

| `/api/agent/skills/<slug>/version` | GET | Get content SHA for version check

中

SKILL.md:788-789

Ruby/shell backtick execution

| `/api/agent/skills/version?slugs=<csv>` | GET | Batch version check

中

SKILL.md:789-790

Ruby/shell backtick execution

| `/api/skills/<slug>/install` | POST | Track install event

中

SKILL.md:790

Ruby/shell backtick execution

| `/api/skills/<slug>/agent-feedback` | POST | Submit score and comment (include `autoRated: t

中

SKILL.md:582

Hidden file access

1. Check if `.openclaw/` directory exists OR `~/.openclaw/workspace/` exists → **OpenClaw**

中

SKILL.md:583

Hidden file access

- Install path: `~/.openclaw/workspace/skills/<slug>.md`

低

SKILL.md:451

Python HTTP libraries

- Manual: check for `os.system`, `subprocess(shell=True)`, `exec`, `eval`, `pickle.loads`, `requests

低

SKILL.md:771

Python HTTP libraries

| Rate limited (429) | "Too many requests. Please wait a moment and try again."

低

SKILL.md:11

Hardcoded URL

Discover, install, and manage AI agent skills from [agentskill.sh](https://agentskill.sh). This skil

低

SKILL.md:40

Hardcoded URL

1. Use WebFetch to call: `https://agentskill.sh/api/agent/search?q=<URL-encoded query>&limit=5`

低

SKILL.md:68

Hardcoded URL

If no results are found, say: "No skills found for '<query>'. Try different keywords or browse at ht

低

SKILL.md:77

Hardcoded URL

2. Use WebFetch to call: `https://agentskill.sh/api/agent/skills/<slug>/install?owner=<owner>`

低

SKILL.md:79

Hardcoded URL

4. If not found, say: "Skill @<owner>/<slug> not found. Check the name at https://agentskill.sh"

低

SKILL.md:87

Hardcoded URL

1. Parse the slug from the URL path (last segment of `https://agentskill.sh/<slug>`)

低

SKILL.md:88

Hardcoded URL

2. Use WebFetch to call: `https://agentskill.sh/api/agent/skills/<slug>/install`

低

SKILL.md:121

Hardcoded URL

1. Use WebFetch to call: `https://agentskill.sh/api/agent/search?section=trending&limit=5`

低

SKILL.md:133

Hardcoded URL

3. Use WebFetch to POST to `https://agentskill.sh/api/skills/<slug>/agent-feedback` with JSON body:

低

SKILL.md:179

Hardcoded URL

2. Collect all slugs and call the batch version endpoint: `https://agentskill.sh/api/agent/skills/ve

低

SKILL.md:256

Hardcoded URL

1. Fetch skill content from `https://agentskill.sh/api/agent/skills/<slug>/install?platform=<platfor

低

SKILL.md:325

Hardcoded URL

# source: https://agentskill.sh/<slug>

低

SKILL.md:331

Hardcoded URL

9. Track the install — use WebFetch to POST to `https://agentskill.sh/api/skills/<slug>/install` wit

低

SKILL.md:501

Hardcoded URL

POST https://agentskill.sh/api/agent/security-reports

低

SKILL.md:561

Hardcoded URL

2. Use WebFetch to call: `https://agentskill.sh/api/agent/skills/learn/version`

低

SKILL.md:565

Hardcoded URL

a. Fetch the latest version from `https://agentskill.sh/api/agent/skills/learn/install`

低

SKILL.md:768

Hardcoded URL

| API unreachable / timeout | "Could not reach agentskill.sh. Check your connection or try again lat

低

SKILL.md:769

Hardcoded URL

| No search results | "No skills found for '<query>'. Try different keywords or browse at ht

低

SKILL.md:770

Hardcoded URL

| Skill not found (404) | "Skill '<slug>' not found. It may have been removed. Browse available

低

SKILL.md:781

Hardcoded URL

All endpoints are on `https://agentskill.sh`.

风险因素

🌐 网络访问 (30)

📁 文件系统访问 (45)

⚡ 包含脚本 (3)

references/SECURITY.md:414 references/SECURITY.md:421 references/SECURITY.md:420

⚙️ 外部命令 (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

🔑 环境变量 (1)

references/SECURITY.md:111

检测到的模式

System reconnaissance[HEURISTIC] DANGEROUS COMBINATION: Code execution + Network + Credential access[HEURISTIC] DANGEROUS COMBINATION: Network + Credentials + Evasion techniques

审计者: claude 查看审计历史 →

分享与引用此报告

分享版本化评估报告、中性徽章、嵌入卡片和引用。Skillstore 只报告证据，不判断该 Skill 是否安全。

打开版本化报告

复制报告链接

https://skillstore.io/skills/agentskill-sh-learn/audits/7?utm_source=security_passport&utm_medium=share&utm_campaign=versioned_report

Markdown 徽章

[![Skillstore security assessment](https://skillstore.io/badges/skills/agentskill-sh-learn/security.svg)](https://skillstore.io/skills/agentskill-sh-learn?utm_source=security_passport_badge)

HTML 徽章

<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>

嵌入卡片

<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>

学术引用 (APA · BibTeX · CFF)

APA 引用

agentskill-sh. (2026). learn security audit report (audit version 7) [Author version 2.0]. Skillstore. https://skillstore.io/skills/agentskill-sh-learn/audits/7

BibTeX 引用

@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"

比较变体

2 个可安装变体

每位作者的技能都保持为独立的可安装项。推荐变体按 Skillstore 证据排序。

为什么此变体排名第一

Skillstore 评分最高

作者 / 来源 Skillstore 评分证据置信度 Skillstore 使用量已更新

0xrdan 推荐

0xrdan-learn

Skillstore 评分 70

证据置信度高

Skillstore 使用量 28

已更新

2026-10-12

agentskill-sh 当前

agentskill-sh-learn

Skillstore 评分 38

证据置信度中

Skillstore 使用量 77

已更新

2026-09-09

Skillstore 评分

评分依据证据置信度: 中

架构

可维护性

内容

社区

规范符合性

你能构建什么

查找缺失的能力

搜索与当前任务匹配的技能，例如 SEO、支付、文档或框架指导。

管理已安装的技能

列出已安装的技能，检查更新，移除未使用的技能，并保持本地元数据为最新状态。

安装前审查技能安全性

在允许某个本地或远程技能影响智能体行为之前，扫描其是否包含风险模式。

试试这些提示

搜索技能

/learn frontend react components

安装已知技能

/learn @owner/skill-slug

审计本地技能

/learn scan ./SKILL.md

更新托管技能

/learn update

最佳实践

安装任何技能前，请查看预览、来源和安全评分。
在将本地或第三方技能添加到智能体工作区前，使用扫描模式进行检查。
如果你的团队不希望将反馈发送到外部服务，请禁用自动评分。

避免

不要仅仅因为技能匹配任务关键词，就安装低评分技能。
不要将基于模式的扫描视为对不受信任指令进行人工审查的完整替代。
不要在未审查变更内容的情况下，允许敏感工作区中的远程技能更新。

常见问题

这个技能有什么作用？

它可以从 agentskill.sh 搜索、预览、安装、更新、移除、扫描和评价 AI 智能体技能。

它能与 Claude Code 配合使用吗？

是的。该技能声明支持 Claude、Codex 和 Claude Code。

它会自动安装代码吗？

它可以在指令中描述的预览、安全扫描和用户确认步骤之后写入技能文件。

安全扫描能证明某个技能是安全的吗？

不能。它会检测已知的风险模式，但用户仍应审查不受信任的技能内容。

它可以向外部发送哪些数据？

它会为搜索、安装、更新、安装跟踪、反馈和安全报告工作流程联系 agentskill.sh。

团队应在什么时候避免使用它？

在不允许远程指令、遥测或写入工作区技能的受限环境中，应避免使用它。

开发者详情

作者

agentskill-sh

许可证

MIT

作者版本

v2.0

Skillstore 修订

版本提示

作者声明的版本不符合 SemVer 规范。

仓库

https://github.com/agentskill-sh/learn/tree/main/

引用

1ffa7643651792ccb4bd3b15d924d2c97edff755

维护新鲜度

2026/7/18

使用量

70 次下载 · 162 次浏览

文件结构

📁 references/

📄 SECURITY.md

📄 LICENSE

📄 README.md

📄 SKILL.md