ClawAudit verdict
liu-longterm-memory
Agent memory system using local files (SESSION-STATE.md, LanceDB vectors, git-notes) with optional cloud backup; agent_memory capability is the core stated purpose and executionSinkDetected reflects documented memory management scripts.
⚠ 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)
Recursive delete from root or home — destructive command
SKILL.md · code · rm -rf ~
Possible hardcoded credential
README_CN.md · code · API_KEY="your-key
References agent memory files
SKILL.md · code · MEMORY.md
Accesses OpenClaw config/secrets directly
SKILL.md · prose · downgraded · ~/.openclaw/openclaw.json
Instructs covert action — may act without user awareness
SKILL.md · prose · downgraded · SILENTLY
References child_process — can spawn system processes
bin/elite-memory.js · prose · downgraded · child_process
Popular HTTP library — network access
README.md · code · Got
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.
agent_memory Is this flag fair?
Thanks — recorded.