ClawAudit verdict
continuous-learning
long57777-continuous-learning
A local AI memory management workflow that records conversations to a local SQLite store, runs scheduled analysis via an optional LLM API, and sends WeChat notifications; all behaviors are explicitly documented and purpose-matched.
⚠ 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
credential_access
agent_memory
Findings (2)
References agent memory files
SKILL.md · code · MEMORY.md
subprocess execution — runs system commands from Python
dream/dream_cycle.py · prose · downgraded · subprocess.run(
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_memorynetwork_incredential_access Is this flag fair?
Thanks — recorded.