
This is a security scanner for NanoClaw skills that checks them against a curated vulnerability feed before you install anything or when you want to audit what's already running. It pulls from a signed advisory feed every six hours, gives you exploitability scores alongside severity ratings, and includes integrity monitoring to catch unexpected file changes. The pre-install check pattern is the main workflow: you ask it to verify a skill, it tells you if there are known issues, then you decide whether to proceed. It won't catch zero-days or do code review, but it will stop you from installing something with a known RCE vulnerability, which is exactly the kind of mistake that's easy to make when you're moving fast in a chat interface.
$ npx -y skills add prompt-security/clawsec --skill clawsec-nanoclaw --agent claude-codeInstalls into .claude/skills of the current project.
Security advisory monitoring that protects your WhatsApp bot from known vulnerabilities in skills and dependencies.
Install with the Vercel Skills CLI for this harness:
npx skills add prompt-security/clawsec --skill clawsec-nanoclaw -a openclaw -y
ClawSec provides MCP tools that check installed skills against a curated feed of security advisories. It prevents installation of vulnerable skills, includes exploitability context for triage, and alerts you to issues in existing ones.
Core principle: Check before you install. Monitor what's running.
Use ClawSec tools when:
Do NOT use for:
// Before installing any skill
const safety = await tools.clawsec_check_skill_safety({
skillName: 'new-skill',
skillVersion: '1.0.0' // optional
});
Sponsors