Caveat verdict

redline

redline-annotate

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

Runs a local HTTP server on 127.0.0.1 to capture annotation feedback and inject it into the agent context via a hook; all operations are local and the architecture is transparently documented.

⚠ 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.

70
security
80
transparency
70
maintenance

Findings (2)

Pattern match high

<script> tag in markdown — potential code injection

injector.sh · prose · downgraded · <script

Pattern match medium

HTTP request to bare IP address — common in malicious payloads

inject.js · prose · downgraded · http://127.0.0.1

Why the tier is capped

Execution sink present in raw bytes (Hard Floor: class B/G). 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.

network_in

Is this flag fair?

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