Caveat verdict

design-engineering

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

Frontend design orchestration framework that explicitly scopes all file operations within the user's project directory and restricts sub-agents to localhost; no external credentials or outbound data flows are present.

⚠ 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.

50
security
100
transparency
90
maintenance

Findings (2)

Pattern match critical

Dynamic Function constructor — equivalent to eval()

references/subagent-patterns.md · code · new Function(

Pattern match high

<script> tag in markdown — potential code injection

references/subagent-patterns.md · prose · downgraded · <script>

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