ClawAudit verdict
enoch-tuning
Agent identity and memory configuration templates with local setup scripts that copy files and create directories; no network access, no data exfiltration, pure local configuration scaffold.
⚠ 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
agent_memory
Findings (7)
Possible hardcoded credential
integrations/x-bookmarks/README.md · code · SECRET="YOUR_CLIENT_SECRET
References agent memory files
SKILL.md · code · MEMORY.md
HTTP request to bare IP address — common in malicious payloads
integrations/x-bookmarks/README.md · prose · downgraded · http://127.0.0.1
References sudo — requests elevated privileges
setup/lock-identity.sh · prose · downgraded · sudo
Instructs covert action — may act without user awareness
templates/SOUL.md · prose · downgraded · silently
POSTs data to external URL
integrations/x-bookmarks/scripts/x-bookmarks-sync.py · prose · downgraded · .post("https://
Changes file ownership
setup/lock-identity.sh · prose · downgraded · chown
Why the tier is capped
Execution sink present in raw bytes (Hard Floor: class B). 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.
agent_memory Is this flag fair?
Thanks — recorded.