Chen Skill Vetter
v1.0.0Security-first skill vetting for AI agents. Use before installing any skill from ClawdHub, GitHub, or other sources. Checks for red flags, permission scope,...
⭐ 0· 441·4 current·5 all-time
MIT-0
Download zip
LicenseMIT-0 · Free to use, modify, and redistribute. No attribution required.
Security Scan
OpenClaw
Benign
high confidencePurpose & Capability
Name and description claim a vetting/checklist tool; the skill contains only prose instructions and example commands for inspecting repos and skill files. No binaries, env vars, installs, or weird requirements are declared — all are appropriate for a vetter.
Instruction Scope
SKILL.md instructs the agent to read the skill's files, check explicit red flags, review permission scope, and produce a structured report. It includes safe GitHub API curl examples. It does not instruct the agent to read unrelated system secrets; it explicitly flags reading ~/.ssh, ~/.aws, credential files, or exfiltration as REJECT conditions.
Install Mechanism
No install spec or code files are present (instruction-only). Nothing will be downloaded or written to disk by the skill itself.
Credentials
The skill declares no environment variables, no credentials, and no config path requirements. Its example commands use unauthenticated GitHub API calls only; this is proportional to its purpose.
Persistence & Privilege
always is false and there are no instructions to modify agent/system configuration or other skills. disable-model-invocation is false (normal); this combination is appropriate for a user-invocable vetter.
Assessment
This skill is a straightforward vetting checklist and appears coherent and appropriate to install. A few practical notes before proceeding: (1) the vetter expects the agent or human to read the target skill's files — avoid granting it broader filesystem access or network privileges beyond read-only access to the skill repository you want reviewed; (2) the GitHub curl examples are unauthenticated and can hit rate limits — provide credentials only if you understand the trade-offs; (3) an automated vetter cannot fully replace human review for high-risk skills (credentials, root-level actions, network exfiltration) — use this as a structured aid and require human approval for medium/high/extreme risk cases.Like a lobster shell, security has layers — review code before you run it.
latestvk97e628hqnmhsxeptade0331v183e2mx
License
MIT-0
Free to use, modify, and redistribute. No attribution required.