ClawAudit verdict
lucid-dreamer
The skill is designed to maintain and improve AI agent memory over time. It does not contain any malicious or deceptive 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.
Findings (3)
Writes to SKILL.md — self-modifying skill
CHANGELOG.md · prose · downgraded · SKILL.md` and `README.md`. Reads today's daily note and write
References agent memory files
ARCHITECTURE.md · code · MEMORY.md
Instructs covert action — may act without user awareness
prompts/nightly-review.md · prose · downgraded · silently
Permissions & capabilities
Requires 3 system binaries. (1 elevated: git).
data_encoding Is this flag fair?
Thanks — recorded.