ClawAudit verdict
lily-memory
lily-memory-5-0-0
The skill appears to be a persistent memory plugin for OpenClaw agents, providing long-term memory and various search features. No malicious or deceptive behavior is detected.
⚠ 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 exec() — may execute shell commands
lib/extraction.js · prose · downgraded · exec(
References child_process — can spawn system processes
lib/sqlite.js · prose · downgraded · child_process
Accesses OpenClaw config/secrets directly
README.md · prose · downgraded · ~/.openclaw/openclaw.json
Dynamic import() — loads module at runtime
test/embeddings.test.js · prose · downgraded · import("
Popular HTTP library — network access
lib/stuck-detection.js · prose · downgraded · 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
Requires 1 system binary.
Is this flag fair?
Thanks — recorded.