ClawAudit verdict
cognitive-brain
A local cross-session memory system backed by PostgreSQL and Redis; data_encoding is for local vector embeddings with no evidence of data exfiltration or malicious behavior.
⚠ 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.
Permission integrity
package_install
Findings (5)
References sudo — requests elevated privileges
docs/INSTALL_GUIDE.md · code · sudo
Pipe to python — executes piped content as Python code
hooks/cognitive-recall/handler.js · prose · downgraded · |Python
References child_process — can spawn system processes
hooks/cognitive-recall/handler.js · prose · downgraded · child_process
Opens WebSocket connection
SKILL.md · prose · downgraded · WebSocket
References agent memory files
CHANGELOG.md · prose · downgraded · MEMORY.md
Why the tier is capped
Execution sink present in raw bytes (Hard Floor: class A/B/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.
package_installdata_encoding Is this flag fair?
Thanks — recorded.