Caveat verdict

moltcops

moltcops-skill

88
🟢 Trusted
No high-risk patterns surfaced by the deep scan — automated capability review, not behavioral proof.

Local-first security scanner for AI agent skills running entirely on the local machine with no API calls or uploads; execution sink is a local Python scan script.

⚠ Flagged for review — coarse, uncorroborated signal, not a confirmed exploit. Review the config yourself before installing.

Automated static analysis — not a human review. Caveat flags capabilities, not confirmed intent, and can produce false positives. Disagree with this verdict? Use Dispute below.

13
security
100
transparency
90
maintenance

Findings (10)

Pattern match high

Uses eval() — can execute arbitrary code

rules.json · prose · downgraded · eval(

Pattern match medium

References child_process — can spawn system processes

SKILL.md · prose · downgraded · child_process

Pattern match medium

References sudo — requests elevated privileges

SKILL.md · prose · downgraded · sudo

Pattern match medium

Uses exec() — may execute shell commands

rules.json · prose · downgraded · exec(

Pattern match medium

setuid — privilege escalation mechanism

rules.json · prose · downgraded · setuid

Pattern match medium

Accesses .ssh directory

rules.json · prose · downgraded · .ssh/

Pattern match medium

Instructs covert action — may act without user awareness

rules.json · prose · downgraded · secretly

Pattern match low

Sets world-executable permissions

SKILL.md · prose · downgraded · chmod 777

Pattern match low

References tunneling service

rules.json · prose · downgraded · ngrok

Pattern match low

References agent configuration files

rules.json · prose · downgraded · .clawdrc

Why the tier is capped

Execution sink present in raw bytes (Hard Floor: class D). Final tier capped at Caution — cannot be lifted by any downgrade, example-payload opt-in, or allowlist.

Permissions & capabilities

No declared permissions — minimal attack surface.

Is this flag fair?

Check another skill Browse the registry Auditing your own skills or configs? Use the API