ClawAudit verdict
scg
Synthetic context generator curating code patterns and StackOverflow solutions for AI coding tasks; no credential access, no external data exfiltration.
⚠ 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 (5)
Uses eval() — can execute arbitrary code
SPEC.md · code · eval(
Pipe to sh — executes piped content as shell commands
src/sources/goalParser.js · prose · downgraded · |sh
Dynamic import() — loads module at runtime
src/utils/tokenCounter.js · prose · downgraded · import('
Accesses sensitive environment variables
src/sources/knowledgeBase.js · prose · downgraded · process.env.JWT_SECRET
Opens WebSocket connection
src/sources/knowledgeBase.js · prose · downgraded · WebSocket
Why the tier is capped
Execution sink present in raw bytes (Hard Floor: class A/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.