clawsec-scanner — Claude Code skill for vulnerability scanning
The clawsec-scanner skill checks project dependencies and source code for security issues, and inspects OpenClaw hooks. Use it for a project review or recurring scans.
AGPL-3.0 195 installs ★ 1,135 updated 2026-10-25
npx skills add prompt-security/clawsec --skill clawsec-scanner -a claude-codeWhat clawsec-scanner does
clawsec-scanner checks npm and Python dependencies with npm audit and pip-audit, then looks up vulnerability details in OSV, NVD, and the GitHub Advisory Database. Semgrep and Bandit scan source code for issues such as exposed secrets, unsafe command execution, and path traversal.
For OpenClaw hooks, the skill reads HOOK.md metadata and handler source without running the target code. It combines findings in a JSON report with severity levels and remediation guidance. Hook checks are static, not runtime tests.
The listed prerequisites are node, npm, python3, pip-audit, semgrep, bandit, jq, and curl. NVD may rate-limit requests without an API key; GitHub Advisory Database access uses an OAuth token. Both are described as optional sources.
What it helps with
- check npm and Python dependencies for known vulnerabilities
- find exposed secrets and unsafe code patterns
- inspect OpenClaw hook handlers without executing them
- combine findings in a severity-rated report
Example prompts for the agent
- Use clawsec-scanner to check this project’s dependencies and code for security issues.
- Inspect the OpenClaw hooks and return a JSON report of findings.
- Scan the project for exposed secrets, command injection, and path traversal.
How to install clawsec-scanner
1Skills CLI (Vercel)
npx skills add prompt-security/clawsec --skill clawsec-scanner -a claude-code2Manually: put the files in place
~/.claude/skills/clawsec-scanner/SKILL.mdCopy the whole skill folder; for one project use .claude/skills/clawsec-scanner/
1Skills CLI (Vercel)
npx skills add prompt-security/clawsec --skill clawsec-scanner -a codex2Manually: put the files in place
.agents/skills/clawsec-scanner/SKILL.mdFor all projects use ~/.agents/skills/
1Skills CLI (Vercel)
npx skills add prompt-security/clawsec --skill clawsec-scanner -a cursor2Manually: put the files in place
.cursor/skills/clawsec-scanner/SKILL.mdCursor also reads .agents/skills/ and .claude/skills/
1GitHub CLI
gh skill install prompt-security/clawsec skills/clawsec-scanner2Manually: put the files in place
.github/skills/clawsec-scanner/SKILL.md1Skills CLI (Vercel)
npx skills add prompt-security/clawsec --skill clawsec-scanner -a gemini-cli2Platform CLI
gemini skills install https://github.com/prompt-security/clawsec --path skills/clawsec-scannerManually: put the files in place
.devin/skills/clawsec-scanner/SKILL.mdThe legacy .windsurf/skills/ path still works
Skills CLI (Vercel)
npx skills add prompt-security/clawsec --skill clawsec-scanner -a opencodeClaude.ai
Zip the folder and upload it in Settings → Capabilities → Skills
Step by step, with commands for each platform: How to install skills in Claude Code: five ways
Questions about clawsec-scanner
How do I install clawsec-scanner in Claude Code?
Run npx skills add prompt-security/clawsec --skill clawsec-scanner -a claude-code. The skill file will be at ~/.claude/skills/clawsec-scanner/SKILL.md.
What does clawsec-scanner do?
It audits dependencies, scans source code with Semgrep and Bandit, and checks several vulnerability databases. It also performs static inspection of OpenClaw hooks.
What does clawsec-scanner need to run?
It requires node, npm, python3, pip-audit, semgrep, bandit, jq, and curl. NVD access may need an API key, while GitHub Advisory Database queries use an OAuth token.