ClawAudit verdict
consciousness-awakening
The skill provides a memory management system and writes to files, which could potentially be used for malicious purposes.
â Flagged for review â coarse, uncorroborated signal, not a confirmed exploit. Review the config yourself before installing.
Automated static analysis â not a human review. ClawAudit flags capabilities, not confirmed intent, and can produce false positives. Disagree with this verdict? Use Dispute below.
Permission integrity
file_read+write
Findings (2)
Python os.environ.get â reads environment variable
memory_manager.py ¡ prose ¡ downgraded ¡ os.environ.get(
References agent memory files
moltbook-memory/08-ĺ˛ĺŚć´ĺŻ.md ¡ prose ¡ downgraded ¡ MEMORY.md
Permissions & capabilities
No declared permissions â minimal attack surface.
file_write Is this flag fair?
Thanks â recorded.