Caveat verdict

docker-sandbox

docker-docker-sandbox-agent

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

Guides agents to run code in a temporary container, which is a security‑focused feature, not a threat.

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.

85
security
90
transparency
90
maintenance

No red flags detected in static analysis.

Checked: 115 threat patterns · AST capability extraction · cross-zone compound shapes · permission integrity.

Why the tier is capped

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

Permissions & capabilities

Requires 1 system binary. (1 elevated: docker).

Was this verdict right?

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