Skill Vetter.Bak

Security-first skill vetting for AI agents. Use before installing any skill from ClawdHub, GitHub, or other sources. Checks for red flags, permission scope,...

This skill is fundamentally coherent: it describes how to vet other skills and gives concrete checks and example commands. Before installing/using it, verify two small issues: (1) the SKILL.md examples use curl and jq but the registry metadata doesn't list required binaries — ensure your agent environment actually has those tools or update the skill to declare them; (2) the _meta.json ownerId/publishedAt differ from the registry metadata shown — confirm the skill author and source to avoid supply-chain confusion. Also remember the vetter will perform network calls (GitHub/raw.githubusercontent) when run — treat network access and fetched content as untrusted and do a manual review for high-risk skills.

Type: OpenClaw Skill Name: skill-vetter-bak Version: 1.0.0 The skill-vetter bundle is a security-focused utility designed to guide AI agents through a structured protocol for auditing other skills. It includes comprehensive checklists for identifying red flags such as data exfiltration, obfuscation, and unauthorized system access, and provides helper commands for inspecting GitHub repository metadata. No malicious logic or suspicious behaviors were found in SKILL.md or _meta.json.