ClawAudit verdict
brigade-handoffs
The skill uses Brigade to set up and troubleshoot handoffs for a repository or agent workspace. It preserves user conventions and treats transcripts and logs as untrusted context. There is no indication of malicious behavior.
โ Flagged for review โ coarse, uncorroborated signal, not a confirmed exploit. Review the config yourself before installing.
Automated static analysis โ 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 (2)
References agent memory files
SKILL.md ยท code ยท MEMORY.md
References agent configuration files
SKILL.md ยท code ยท CLAUDE.md
Permissions & capabilities
No declared permissions โ minimal attack surface.
data_encodingagent_memory Is this flag fair?
Thanks โ recorded.