Skill Vetter Jarvis
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· 44·0 current·0 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 match the content of SKILL.md: a checklist and commands for vetting other skills. No unrelated environment vars, binaries, or installs are requested.
Instruction Scope
SKILL.md stays on-topic: it instructs reviewing skill files, checking for obvious red flags, and gives GitHub API curl examples. It does not direct reading system files or exfiltrating data beyond the expected GitHub queries. The directive to "Read ALL files in the skill" is appropriate for a vetting tool (it targets the skill bundle, not arbitrary system files).
Install Mechanism
No install spec and no code files — the skill is instruction-only, which minimizes risk. Nothing is downloaded or executed by the skill itself.
Credentials
No required environment variables, credentials, or config paths are declared. The vetting instructions specifically mark credential requests and access to ~/.ssh, ~/.aws, etc., as red flags.
Persistence & Privilege
Flags use default (always:false) and model invocation is allowed (normal). There is no request for permanent presence or changes to other skills' configs. Note: because disable-model-invocation is false, an agent could invoke this skill autonomously — appropriate for a vetting helper but worth noting.
Assessment
This skill is an instruction-only vet checklist and appears coherent with its stated purpose. Before using it: 1) Ensure your agent environment has curl and jq if you want to run the example quick-commands (SKILL.md does not declare required binaries). 2) When following its advice, ensure the agent reads only the skill bundle files (not arbitrary home directories) — vetting should not grant the agent blanket access to your ~/.ssh, ~/.aws, or other sensitive paths. 3) The _meta.json version (1.0.1) differs from the SKILL.md header (1.0.0); this is minor but you may want to confirm the canonical version. 4) Do not let automated vetting be the sole decision-maker for high-risk skills — follow its checklist and require human review for medium/high/extreme findings.Like a lobster shell, security has layers — review code before you run it.
latestvk97efx1a709rd04ppceyjqjay1845dtq
License
MIT-0
Free to use, modify, and redistribute. No attribution required.