ClawAudit verdict
prd-fullstack
prd-skill-workflow2
The skill generates a full-stack PRD (Product Requirements Document) collaboration workflow. It does not contain any malicious code or intent.
⚠ Flagged for review — coarse, uncorroborated signal, not a confirmed exploit. Review the config yourself before installing.
Automated static analysis — not a human review. ClawAudit flags capabilities, not confirmed intent, and can produce false positives. Disagree with this verdict? Use Dispute below.
Findings (4)
<script> tag in markdown — potential code injection
scripts/score.js · prose · downgraded · <script
Opens WebSocket connection
prompts/step8-tech.md · code · WebSocket
Uses exec() — may execute shell commands
scripts/validate.js · prose · downgraded · exec(
References child_process — can spawn system processes
templates/update.js · prose · downgraded · child_process
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?
Thanks — recorded.