Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add suryast/free-ai-agent-skills --skill skill-securitygit clone --depth 1 https://github.com/suryast/free-ai-agent-skillsWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/suryast/free-ai-agent-skills/skill-security)<a href="https://agentmods.dev/skills/suryast/free-ai-agent-skills/skill-security"><img src="https://agentmods.dev/badge/skills/suryast/free-ai-agent-skills/skill-security/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/suryast/free-ai-agent-skills/skill-security"><img src="https://agentmods.dev/badge/skills/suryast/free-ai-agent-skills/skill-security.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00062 | $0.00810 |
| Opus 5 | $0.00031 | $0.00405 |
| Sonnet 5 | $0.00012 | $0.00162 |
| Haiku 4.5 | $0.00006 | $0.00081 |
Grade A, and why
skill-security scanned grade A with 2 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 11d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
| **Network Exfiltration** | 🚨 HIGH | `requests.`, `urllib`, `http.client`, `socket.`, `fetch(`, `axios` | Runs shell commandslowCapability
Expected in a hook, worth knowing in a rule or an instructions file.
| **Subprocess Abuse** | ⚠️ MEDIUM | `subprocess.run`, `os.system`, `child_process` with credentials | How it starts
The opening of the file, as written. The whole thing — 89 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Skill Security Scanner
Security audit tool for AI agent skills. Run before installing any new skill.
Quick Audit
# Audit a skill directory
./skill-security/audit.sh /path/to/skill
# Audit all installed skills
./skill-security/audit-all.sh
What It Checks
| Check | Risk Level | Pattern |
|---|---|---|
| Network Exfiltration | 🚨 HIGH | requests., urllib, http.client, socket., fetch(, axios |
| Credential Harvesting | 🚨 HIGH | .ssh/, .aws/, pass , keyring, credential, secret, token file reads |
| Code Injection | 🚨 CRITICAL | exec(, eval(, compile(, Function(, __import__ |
| Obfuscation | ⚠️ MEDIUM | base64.decode, atob, encoded payloads |
| Env Dumping | ⚠️ MEDIUM | os.environ, process.env, getenv bulk access |
| Subprocess Abuse | ⚠️ MEDIUM | subprocess.run, os.system, child_process with credentials |
Severity Levels
- CRITICAL (🚨): Block installation, report to owner
- HIGH (🔴): Requires manual review before use
- MEDIUM (🟡): Note but allow if from trusted source
- LOW (🟢): Informational only
Safe Skill Checklist
Before using any skill:
- ✅ Is it from a trusted source? (official OpenClaw, known publisher)
- ✅ Is the code readable (not obfuscated)?
- ✅ Does it document why it needs network/credential access?
- ✅ Does it scope file access to its own directory?
- ✅ Has it been audited by the community?
Integration with AGENTS.md
Add this to your workflow:
## Skill Installation Protocol
Before loading any new skill:
1. Run `./skill-security/audit.sh <skill-path>`
2. If CRITICAL/HIGH findings → STOP, alert the user
3. If MEDIUM findings → Review manually, proceed if justified
4. If CLEAN → Safe to use
Automatic Protection
The scanner creates a blocklist at ./blocklist.txt.
Skills with CRITICAL findings are automatically added.
Manual Override
If a skill is flagged but you've verified it's safe:
What ships with it
5 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 11d ago First seen · 89 lines · 62 tokens per session scan A a3993ff80a36
skill-security is a skill published in the GitHub repository suryast/free-ai-agent-skills (2 stars, last pushed today), licensed MIT. It adds 62 tokens to every session and 810 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it A with 2 findings (makes network calls, runs shell commands). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
9router-web-fetch
Fetch URL → markdown / text / HTML via 9Router /v1/web/fetch using Ollama Cloud / Firecrawl / Jina Reader / Tavily Extract / Exa Contents. Use when the user wants to scrape a webpage, extract URL content, read article, or convert a URL to markdown.
9router-web-search
Web and X search via 9Router /v1/search using Tavily / Exa / Brave / Serper / SearXNG / Google PSE / Linkup / SearchAPI / You.com / Perplexity / Xquik. Use when the user wants to search the web, find articles, or search public X posts.
9router-stt
Speech-to-text via 9Router /v1/audio/transcriptions using OpenAI Whisper / Groq / Gemini / Deepgram / AssemblyAI / NVIDIA / HuggingFace models. Use when the user wants to transcribe audio, convert speech to text, or get subtitles from audio files.
9router
Entry point for 9Router — local/remote AI gateway with OpenAI-compatible REST for chat, image, TTS, embeddings, web search, web fetch. Use when the user mentions 9Router, NINEROUTERURL, or wants AI without writing provider boilerplate. This skill covers setup + indexes capability skills; fetch the relevant capability…
9router-embeddings
Generate vector embeddings via 9Router /v1/embeddings using OpenAI / Gemini / Mistral / Voyage / Nvidia / GitHub embedding models for RAG, semantic search, similarity. Use when the user wants embeddings, vectors, RAG, semantic search, or to embed text.
example
Example fixture skill for scanner regression coverage.