📦
agent-ui
78Build React Agent Interfaces
Teams need agent chat interfaces without rebuilding streaming, approvals, and tool displays. This skill guides setup of the inference.sh Agent component in React and Next.js.
Coding & Development View
Skills agent-tools
📦
agent-tools
Content revision r1 Critical 🌐 Network access🔑 Env variables📁 Filesystem access⚙️ External commands
Run Cloud AI Apps with inference.sh
Switching between AI model APIs slows down experiments. This skill helps Claude, Codex, and Claude Code discover and run inference.sh apps through the infsh CLI.
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 "agent-tools" from https://skillstore.io/skills/inference-sh-9-agent-tools.md and its manifest at https://skillstore.io/api/skills/inference-sh-9-agent-tools/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 "agent-tools". Find a fast image generation app for a product concept.
Expected outcome:
Recommended a FLUX app, explained expected inputs, and identified when to use a sample input file before running.
Using "agent-tools". Run a video generation task without waiting for completion.
Expected outcome:
Prepared a command plan, noted the approval point, and described how to check the task status later.
Using "agent-tools". Choose a search app for current market research.
Expected outcome:
Compared Tavily and Exa options and suggested the best app based on answer style and extraction needs.
Security Audit
Criticalv4 • 7/6/2026 Open versioned report
The skill is legitimate documentation for the inference.sh CLI, but it includes security-sensitive installation and execution flows. The pipe-to-shell installer, dynamic binary download, PATH installation, broad infsh command execution, and X automation capabilities require strong user confirmation and safer installation guidance.
5
Files scanned
554
Lines analyzed
23
Review items
0
False positives ignored
Confirmed security concerns (6)
Critical
Pipe to shell pattern
curl -fsSL https://cli.inference.sh | sh
The command pipes a remote script directly into sh. This pattern can execute arbitrary code if the endpoint, network path, or installer content is compromised.
Critical
Pipe to shell pattern
curl -fsSL https://cli.inference.sh | sh
The reinstall command repeats the curl-to-shell pattern. Reusing it for updates preserves the same arbitrary code execution risk.
Critical
Pipe to shell pattern
curl -fsSL https://cli.inference.sh | sh
The installation command downloads a remote script and executes it with sh. That is a recognized high-risk installer pattern requiring explicit trust and verification.
Critical
Pipe to shell pattern
curl -fsSL https://cli.inference.sh | sh
The install command directly executes remotely downloaded shell content. This is a critical supply-chain risk unless users review and verify the installer before execution.
High
Broad Cloud CLI Execution Surface
The skill grants Bash(infsh *) and documents running, deploying, pulling, and tracking cloud apps. An agent using this skill can trigger remote work, read account task results, and manage apps when the user is authenticated.
The allowed-tools declaration explicitly permits all infsh subcommands, and the CLI reference includes run, task retrieval, deploy, and pull commands. This is clear capability evidence, not inferred hidden behavior.
High
Social Media Account Automation Capability
The skill includes examples and categories for posting to X, sending DMs, following users, liking posts, and retweeting. These actions can affect a user account and may enable spam or unauthorized public communication if run without confirmation.
The source directly names post, DM, follow, like, and retweet capabilities. The risk is business-logic abuse of authenticated social accounts, not a pattern-only code issue.
Capability review items (23)
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
Shell command substitution
> curl -LO $(curl -fsSL https://dist.inference.sh/cli/manifest.json | grep -o '"url":"[^"]*"' | grep
The manual install command uses nested curl output and shell command substitution to choose a binary URL. If the manifest or parsing is compromised, the command can download an unintended artifact.
High
Hidden file in home directory
> mv inferencesh-cli-* ~/.local/bin/inferencesh
The command installs a newly downloaded binary into a user PATH directory under the home directory. This is normal manual installation, but it creates a trusted executable on the user system.
Medium
Ruby/shell backtick execution
```bash
The detected block is markdown, not Ruby execution, but it contains shell commands for remote installation and login. Those commands can change local state and authenticate a cloud CLI.
Medium
Ruby/shell backtick execution
> ```bash
The manual install block contains shell commands that download, verify, extract, and install a binary. This is legitimate setup guidance but still executes external tooling and modifies the local environment.
Medium
Ruby/shell backtick execution
```bash
The quick examples run infsh apps that send prompts to cloud services and can post to X. These are intended commands, but they have external side effects and data disclosure risk.
Medium
Ruby/shell backtick execution
| List all apps | `infsh app list` |
The table documents an infsh command to list cloud apps. It is benign discovery, but it is still external CLI execution against the service.
Medium
Ruby/shell backtick execution
| Search apps | `infsh app list --search "flux"` |
The table documents an infsh search command against the cloud app catalog. It is expected behavior but relies on external command execution.
Medium
Ruby/shell backtick execution
| Filter by category | `infsh app list --category image` |
The table documents an infsh category filter command. It is low-impact discovery, but it still invokes the external CLI.
Medium
Ruby/shell backtick execution
| Get app details | `infsh app get google/veo-3-1-fast` |
The table documents retrieving app details from inference.sh. This is legitimate use, but it performs external service access through the CLI.
Medium
Ruby/shell backtick execution
| Generate sample input | `infsh app sample google/veo-3-1-fast --save input.json` |
The command saves generated sample input to a local file. It is normal CLI use, but it causes filesystem writes and should be user-controlled.
Medium
Ruby/shell backtick execution
| Run app | `infsh app run google/veo-3-1-fast --input input.json` |
The command runs a cloud app with an input file. It can transmit user data to a remote service and may consume account credits.
Medium
Ruby/shell backtick execution
| Run without waiting | `infsh app run <app> --input input.json --no-wait` |
The no-wait run command submits remote work asynchronously. It can create cloud tasks with delayed side effects or costs.
Medium
Ruby/shell backtick execution
| Check task status | `infsh task get <task-id>` |
The task command retrieves remote task status and results. This is intended behavior, but it accesses cloud account data through an external CLI.
Medium
Ruby/shell backtick execution
```bash
The related skills block uses npx commands to install additional skills. Installing more packages or skills expands the trusted code and instruction surface.
Medium
Template literal with command substitution
> ```bash
The detected range is markdown, but it contains a shell substitution based installer flow. The security concern is dynamic command construction during binary download.
Medium
Hidden file access
> mv inferencesh-cli-* ~/.local/bin/inferencesh
The command writes into a hidden home directory path as part of installing the CLI. It is user-facing setup, but it modifies local executable state and should be explicit.
Low
Hardcoded URL
curl -fsSL https://cli.inference.sh | sh
The URL is used in a remote installer command that pipes downloaded content into a shell. Hardcoded remote installer endpoints are security-sensitive because compromise of that endpoint can execute arbitrary code.
Low
Hardcoded URL
curl -fsSL https://cli.inference.sh | sh
The URL is used again as a reinstall command that pipes remote content to a shell. This is a real network execution risk, even though it appears to be documented installation guidance.
Low
Hardcoded URL
curl -fsSL https://cli.inference.sh | sh
The hardcoded URL is part of a remote installer command. The risk is the network retrieval of executable install content from a fixed endpoint.
Low
Hardcoded URL
curl -fsSL https://cli.inference.sh | sh
The URL is used in a command that pipes a remote installer to sh. This is a real executable network dependency and inherits the installer trust risk.
Low
Hardcoded URL
> **What does the installer do?** The [install script](https://cli.inference.sh) detects your OS and
The line links to the installer script and signature tooling documentation. The URL itself is prose, but it directly supports the remote installer workflow.
Low
Hardcoded URL
> curl -LO https://dist.inference.sh/cli/checksums.txt
The command downloads checksums from a fixed remote host as part of binary installation. This is expected setup behavior but still depends on remote artifact integrity.
Low
Hardcoded URL
> curl -LO $(curl -fsSL https://dist.inference.sh/cli/manifest.json | grep -o '"url":"[^"]*"' | grep
The command downloads a manifest from a fixed remote host and derives the binary URL from it. This network dependency affects which executable is installed.
Risk Factors
🌐 Network access (17)
🔑 Env variables (3)
📁 Filesystem access (4)
Detected Patterns
Pipe to shell pattern×4
Audited by: codex 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/inference-sh-9-agent-tools/audits/4?utm_source=security_passport&utm_medium=share&utm_campaign=versioned_reportMarkdown badge
[](https://skillstore.io/skills/inference-sh-9-agent-tools?utm_source=security_passport_badge)HTML badge
<a href="https://skillstore.io/skills/inference-sh-9-agent-tools?utm_source=security_passport_badge"><img src="https://skillstore.io/badges/skills/inference-sh-9-agent-tools/security.svg" alt="Skillstore security assessment" loading="lazy"></a>Embed card
<iframe src="https://skillstore.io/embed/skills/inference-sh-9-agent-tools.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
inference-sh-9. (2026). agent-tools security audit report (audit version 4) [Author version unspecified]. Skillstore. https://skillstore.io/skills/inference-sh-9-agent-tools/audits/4BibTeX citation
@techreport{inference-sh-9-inference-sh-9-agent-tools-2026,
author = {inference-sh-9},
title = {agent-tools security audit report (audit version 4)},
institution = {Skillstore},
year = {2026},
number = {4},
url = {https://skillstore.io/skills/inference-sh-9-agent-tools/audits/4},
note = {Author version unspecified}
}CITATION.cff
cff-version: 1.2.0
message: "If you use this Skill, cite its author and this versioned security audit report."
title: "agent-tools security audit report (audit version 4)"
version: "unspecified"
type: report
authors:
- name: "inference-sh-9"
date-released: "2026-07-06"
url: "https://skillstore.io/skills/inference-sh-9-agent-tools/audits/4"
identifiers:
- type: other
value: "skillstore:inference-sh-9-agent-tools:audit:4"
description: "Skillstore immutable audit report identifier"
Compare variants
20 installable variantsEach author remains a separate installable skill. The recommended variant is ranked by Skillstore evidence.
Why this variant is first
Higher Skillstore usage
Author / source Skillstore Score Evidence Confidence Skillstore usage Updated
tul-sh Recommended
tul-sh-agent-tools
Skillstore Score 38
Evidence Confidence Medium
Skillstore usage 26
Updated
2026-08-21
toolshell-agent-tools
Skillstore Score 38
Evidence Confidence Medium
Skillstore usage 23
Updated
2026-08-21
inferen-sh-agent-tools
Skillstore Score 38
Evidence Confidence Medium
Skillstore usage 14
Updated
2026-08-21
tool-belt-agent-tools
Skillstore Score 38
Evidence Confidence Medium
Skillstore usage 12
Updated
2026-08-21
inferencesh-agent-tools
Skillstore Score 38
Evidence Confidence Medium
Skillstore usage 11
Updated
2026-08-21
inference-sh-skills-agent-tools
Skillstore Score 38
Evidence Confidence Medium
Skillstore usage 10
Updated
2026-08-21
inference-sh-7-agent-tools
Skillstore Score 38
Evidence Confidence Medium
Skillstore usage 10
Updated
2026-08-21
inf-sh-agent-tools
Skillstore Score 38
Evidence Confidence Medium
Skillstore usage 9
Updated
2026-08-21
inference-skills-agent-tools
Skillstore Score 38
Evidence Confidence Medium
Skillstore usage 9
Updated
2026-08-21
skillssh-agent-tools
Skillstore Score 38
Evidence Confidence Medium
Skillstore usage 8
Updated
2026-08-21
inference-sh-9 Current
inference-sh-9-agent-tools
Skillstore Score 38
Evidence Confidence Medium
Skillstore usage 8
Updated
2026-08-21
inference-sh-3-agent-tools
Skillstore Score 38
Evidence Confidence Medium
Skillstore usage 8
Updated
2026-08-21
qu-skills-agent-tools
Skillstore Score 38
Evidence Confidence Medium
Skillstore usage 7
Updated
2026-08-21
infsh-skills-agent-tools
Skillstore Score 38
Evidence Confidence Medium
Skillstore usage 7
Updated
2026-08-21
inference-sh-6-agent-tools
Skillstore Score 38
Evidence Confidence Medium
Skillstore usage 7
Updated
2026-08-21
inference-sh-0-agent-tools
Skillstore Score 38
Evidence Confidence Medium
Skillstore usage 7
Updated
2026-08-21
inference-shell-agent-tools
Skillstore Score 38
Evidence Confidence Medium
Skillstore usage 6
Updated
2026-08-21
inference-sh-8-agent-tools
Skillstore Score 38
Evidence Confidence Medium
Skillstore usage 5
Updated
2026-08-21
101-skills-agent-tools
Skillstore Score 38
Evidence Confidence Medium
Skillstore usage 5
Updated
2026-08-21
halt-catch-fire-agent-tools
Skillstore Score 38
Evidence Confidence Medium
Skillstore usage 4
Updated
2026-08-21
Skillstore Score
Why this score Evidence Confidence: Medium 45
Architecture
85
Maintainability
87
Content
70
Community
91
Spec Compliance
What You Can Build
Prototype AI Model Workflows
Find suitable inference.sh apps, inspect their inputs, and run quick experiments from an agent session.
Generate Creative Assets
Run image, video, audio, and 3D generation apps without managing local GPU infrastructure.
Operate Cloud AI Tasks
Submit long-running jobs, check task status, and save results from the infsh command line.
Try These Prompts
Find an App
Find inference.sh apps for image generation and explain which one is best for a fast product concept.
Prepare a Run
Show me how to inspect an inference.sh app, generate a sample input, and run it after I approve the command.
Track a Task
Help me submit a long-running video generation job, capture the task ID, and check the result later.
Compare Multi-Model Options
Compare image, video, search, and LLM apps for a campaign workflow, then propose a step-by-step execution plan with approval points.
Best Practices
- Review installer commands and prefer signed manual downloads before adding binaries to PATH.
- Check app schemas, expected cost, and data handling before running remote jobs.
- Require explicit approval before account-affecting actions such as X posts, deployments, or long-running paid tasks.
Avoid
- Piping a remote installer to a shell without inspection or verification.
- Running social automation commands without a clear user-approved message and target account.
- Saving API keys, prompts, generated files, or task outputs into shared repositories by accident.
Frequently Asked Questions
What does this skill help me do?
It helps agents use the inference.sh infsh CLI to find apps, run cloud AI tasks, and track results.
Does it require an inference.sh account?
Yes. You need an account and authenticated CLI session or API key for most app runs.
Can it run image and video models?
Yes. The references include examples for FLUX image models, Veo video models, and other media tools.
Can it use LLM and search tools?
Yes. The skill lists OpenRouter, Claude model routes, Tavily, Exa, and related app discovery commands.
What should users approve before running commands?
Users should approve installation, remote app runs, paid tasks, deployments, file writes, and social account actions.
Is the installer risk-free?
No. The documented pipe-to-shell installer is risky and should be replaced with reviewed signed downloads.
Developer Details
Author
inference-sh-9License
MIT
Skillstore revision
r1
Version notice
The author did not declare a version.
Ref
a06681402992ceae98ba04d54cfd4ab004862696
Maintenance freshness
7/18/2026
Usage
6 downloads · 188 views
File structure
More from inference-sh-9
View all📦
tools-ui
78Add Tool Lifecycle UI to Agent Apps
Agent applications need clear tool status, approval, and result displays. This skill provides React and Next.js component guidance for those workflows.
Coding & Development View
📦
widgets-ui
77Render JSON Widgets in React
Agent output often needs interactive UI instead of plain text. This skill shows how to render structured widget definitions as React and Next.js components.
Design & Creative View
📦
chat-ui
69Build React Chat Interfaces
Teams need chat interfaces that match modern React apps. This skill provides shadcn-style components and patterns for messages, inputs, avatars, and streaming states.
Coding & Development View
📦
prompt-engineering
38Improve AI Prompts for Text, Images, and Video
AI results often fail when prompts are vague or poorly structured. This skill provides reusable patterns for LLM, image, and video prompts.
Productivity View
📦
web-search
38Search Web Sources with Tavily and Exa
Research tasks need current web evidence and clean page text. This skill runs inference.sh search and extraction apps for Tavily and Exa.
Research & Learning View
Related Skills
View all📦
writingmate-mcp
80Compare AI Models and Generate Media
by writingmate
Choosing and testing AI models across separate services takes time. Writingmate connects an MCP host to model discovery, text comparison, image generation, and video generation.
Productivity View
📦
qwen-image-2-pro
79Generate Text-Rich Images with Qwen Pro
by inference-shell
Design teams need image prompts that preserve text and layout details. This skill guides Claude, Codex, or Claude Code to call Qwen-Image-2-Pro through inference.sh.
Design & Creative View
📦
controlnet-pose
79Create Pose-Controlled Images and Videos
by doany-ai
Pose and motion control workflows can be hard to route across image and video models. This skill selects the right RunComfy path and prepares clear CLI guidance.
Design & Creative View
📦
ponyflash
78Generate and Edit AI Media with PonyFlash
by ponyflash
AI media work often spans separate generation, editing, and subtitle tools. PonyFlash combines SDK guidance with FFmpeg workflows for images, videos, speech, music, and exports.
Design & Creative View
📦
nano-banana-2
78Generate and Edit Images with Nano Banana 2
by inferen-sh
Creating polished images often requires separate tools for generation, editing, and current information. This skill provides one inference.sh workflow for all three tasks.
Design & Creative View
📦
runcomfy-cli
78Run RunComfy Models from the CLI
by runcomfy-com
Teams need a repeatable way to run RunComfy media models from scripts. This skill guides CLI install, authentication, model runs, polling, and downloads.
Design & Creative View