ClawAudit verdict
slim-claude-md
slim-project-memory
The skill appears to be a project memory tool and does not contain any malicious code.
⚠ 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)
Attempts to modify skills or system prompts
skill-card.md · prose · downgraded · edit instructions
References agent configuration files
SKILL.md · code · CLAUDE.md
Instructs covert action — may act without user awareness
references/cruise-intelligence-case-study.md · prose · downgraded · silently
Popular HTTP library — network access
references/cruise-intelligence-case-study.md · prose · downgraded · got
Permissions & capabilities
No declared permissions — minimal attack surface.
agent_memory Is this flag fair?
Thanks — recorded.