Caveat verdict

skill-sandbox

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

Sandboxed installation pipeline staging skills, running 5-layer security scan, auto-promoting clean or quarantining flagged skills; all operations are local with no external data transmission.

⚠ 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.

38
security
70
transparency
70
maintenance

Findings (4)

Pattern match high

Uses eval() — can execute arbitrary code

SKILL.md · prose · downgraded · eval(

Pattern match high

Dynamic Function constructor — equivalent to eval()

SKILL.md · prose · downgraded · new Function(

Pattern match high

Recursive delete from root or home — destructive command

scripts/skill-sandbox.sh · prose · downgraded · rm -rf /

Pattern match low

Sets world-executable permissions

SKILL.md · prose · downgraded · chmod 777

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