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 SkillsCatalog/registry --skill skill-safety-scannergit clone --depth 1 https://github.com/SkillsCatalog/registryWrote 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/skillscatalog/registry/skill-safety-scanner)<a href="https://agentmods.dev/skills/skillscatalog/registry/skill-safety-scanner"><img src="https://agentmods.dev/badge/skills/skillscatalog/registry/skill-safety-scanner.svg" alt="Measured on agentmods" 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 | $0.00029 | $0.00566 |
| Opus 5 | $0.00015 | $0.00283 |
| Sonnet 5 | $0.00006 | $0.00113 |
| Haiku 4.5 | $0.00003 | $0.00057 |
Grade A, and why
skill-safety-scanner scanned grade A with 1 finding 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 7d 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.
Runs shell commandslowCapability
Expected in a hook, worth knowing in a rule or an instructions file.
Code: subprocess.run(cmd, shell=True) How it starts
The opening of the file, as written. The whole thing — 109 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Instructions
Use this skill to run safety scans on any Agent Skill directory before publishing. The scanner detects:
- Secrets - Hardcoded API keys, tokens, passwords, private keys
- Dangerous Code - eval(), exec(), command injection, XSS patterns
- Permissions - Required capabilities (filesystem, network, subprocess, etc.)
When to Use
- Before submitting a skill for publication
- To preview what the catalog safety scan will find
- To identify and fix security issues early
- As part of CI/CD pipelines
How to Use
Scan a skill directory:
Scan the skill at /path/to/my-skill for safety issues
Get detailed output:
python3 safety_scan.py /path/to/my-skill --verbose
Get JSON output for CI integration:
python3 safety_scan.py /path/to/my-skill --json
Output
Safety Scan Report
Skill: my-skill
Grade: B (85/100)
Scores:
Secrets: 100/100
Dangerous Code: 70/100
Permissions Detected:
- filesystem
- network
Findings (1):
[medium] Potential command injection
File: scripts/main.py:42
Code: subprocess.run(cmd, shell=True)
Recommendation: Review the finding above before publishing.
Examples
Basic scan:
User: Scan my skill at ./document-tools for safety issues
Agent: Running safety scan on ./document-tools...
Grade: A (95/100)
No critical issues found.
Finding secrets:
User: Check ./my-api-client for security issues
Agent: Running safety scan...
Grade: F (0/100)
Findings:
[critical] Hardcoded API key detected
File: config.py:5
Code: API_KEY = "sk-ant-..."
You must remove this secret before publishing.
Limitations
- Does not scan dependencies (use npm audit / pip-audit separately)
- Pattern-based detection may have false positives
- Cannot detect all security issues (not a replacement for security review)
- Scans local files only (not GitHub URLs)
Dependencies
- Python 3.9+
- No external dependencies (uses Python stdlib)
What ships with it
2 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.
- 7d ago First seen · 109 lines · 29 tokens per session scan A 8bc4b067e561
skill-safety-scanner is a skill published in the GitHub repository SkillsCatalog/registry (1 stars, last pushed 8mo ago), licensed MIT. It adds 29 tokens to every session and 566 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it A with 1 finding (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
writing-rules
Creates behavioral rules in markdown to block dangerous commands or restrict AI behavior. Use when adding safety guardrails or preventing specific commands.
safety-checks
Verify before you trust — model pinning, fallbacks, and runtime safety validation.
qa-acceptance
Produce QA acceptance criteria and a manual validation plan for a feature change — golden path, edge cases, error states, performance limits, and explicit pass/fail evidence.
edgeone-clawscan
The first security skill to install after setting up OpenClaw — powered by Tencent Zhuque Lab. Works like an antivirus for your AI environment: audits installed skills, scans skills before installation, and performs a full OpenClaw security health check to prevent data leaks and privacy risks. Backed by Tencent Zhuque…
edgeone skill scanner
A local static scanner that checks agent-skill files for security risks before they are installed or used. Static analysis examines files without running them.
smiles-validation
Strict SMILES validation, structural comparison, and modification verification. Catches invalid LLM-generated molecules.