clawsec-clawhub-checker — Claude Code skill
clawsec-clawhub-checker — a skill that vets code before installation by checking ClawHub reputation scores, scanner status, and authorship history. Install it if you want an extra approval layer for skill installs across your environments.
AGPL-3.0 259 installs ★ 1,135 updated 2026-10-25
npx skills add prompt-security/clawsec --skill clawsec-clawhub-checker -a claude-codeWhat clawsec-clawhub-checker does
clawsec-clawhub-checker layers a reputation gate on top of clawsec-suite. It queries ClawHub metadata, evaluates scanner status (including VirusTotal when available), applies reputation heuristics based on age, update frequency, author track record, and download count, then requires explicit --confirm-reputation if the score falls below the threshold.
Requires node, clawhub, and openclaw in PATH, plus a prior installation of clawsec-suite. The skill calls ClawHub inspect and search endpoints to gather reputation data. Scores are heuristic-based and scanners can produce false positives and negatives, so treat this as defense-in-depth, not a guarantee.
What it helps with
- check a skill's reputation before installing it
- require approval for low-scoring skills
- review scanner verdicts including VirusTotal
- layer reputation checks into clawsec-suite workflows
Example prompts for the agent
- Install
some-skillversion 1.0.0 with reputation check:node ~/.openclaw/skills/clawsec-clawhub-checker/scripts/enhanced_guarded_install.mjs --skill some-skill --version 1.0.0 - Override a low reputation score:
node ~/.openclaw/skills/clawsec-clawhub-checker/scripts/enhanced_guarded_install.mjs --skill some-skill --version 1.0.0 --confirm-reputation - Validate your reputation hook setup:
node ~/.openclaw/skills/clawsec-clawhub-checker/scripts/setup_reputation_hook.mjs
How to install clawsec-clawhub-checker
1Skills CLI (Vercel)
npx skills add prompt-security/clawsec --skill clawsec-clawhub-checker -a claude-code2Manually: put the files in place
~/.claude/skills/clawsec-clawhub-checker/SKILL.mdCopy the whole skill folder; for one project use .claude/skills/clawsec-clawhub-checker/
1Skills CLI (Vercel)
npx skills add prompt-security/clawsec --skill clawsec-clawhub-checker -a codex2Manually: put the files in place
.agents/skills/clawsec-clawhub-checker/SKILL.mdFor all projects use ~/.agents/skills/
1Skills CLI (Vercel)
npx skills add prompt-security/clawsec --skill clawsec-clawhub-checker -a cursor2Manually: put the files in place
.cursor/skills/clawsec-clawhub-checker/SKILL.mdCursor also reads .agents/skills/ and .claude/skills/
1GitHub CLI
gh skill install prompt-security/clawsec skills/clawsec-clawhub-checker2Manually: put the files in place
.github/skills/clawsec-clawhub-checker/SKILL.md1Skills CLI (Vercel)
npx skills add prompt-security/clawsec --skill clawsec-clawhub-checker -a gemini-cli2Platform CLI
gemini skills install https://github.com/prompt-security/clawsec --path skills/clawsec-clawhub-checkerManually: put the files in place
.devin/skills/clawsec-clawhub-checker/SKILL.mdThe legacy .windsurf/skills/ path still works
Skills CLI (Vercel)
npx skills add prompt-security/clawsec --skill clawsec-clawhub-checker -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-clawhub-checker
How do I install clawsec-clawhub-checker in Claude Code?
Run npx skills add prompt-security/clawsec --skill clawsec-clawhub-checker -a claude-code, then check ~/.claude/skills/clawsec-clawhub-checker/SKILL.md.
What does clawsec-clawhub-checker do?
It evaluates ClawHub reputation before skill installation, checking scanner results, authorship history, and other heuristics. When a score is below the threshold (default 70), the skill asks for explicit confirmation via --confirm-reputation flag.
What do I need to run this skill?
You need node, clawhub, and openclaw in PATH, plus clawsec-suite already installed. Set the reputation threshold via the CLAWHUB_REPUTATION_THRESHOLD environment variable (0–100).