ClawAudit verdict
reflect
reflect-learn
The skill seems to be a self-improvement tool through conversation analysis with no indication of malicious intent.
⚠ 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 (4)
Pipe to python — executes piped content as Python code
hooks/README.md · prose · downgraded · | python
References agent configuration files
references/agent_mappings.md · code · CLAUDE.md
References agent memory files
SKILL.md · prose · downgraded · MEMORY.md
Python os.environ.get — reads environment variable
hooks/precompact_reflect.py · prose · downgraded · os.environ.get(
Permissions & capabilities
No declared permissions — minimal attack surface.
agent_memory Is this flag fair?
Thanks — recorded.