ClawAudit verdict
jarvis-core
jarvis-core-angelofalhashmi
Personality/behavior framework for an AI assistant with memory and self-improvement capabilities; dynamic_eval is used for its own internal memory management, not for executing untrusted external 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 (2)
References agent memory files
SKILL.md · code · MEMORY.md
References agent configuration files
README.md · prose · downgraded · CLAUDE.md
Permissions & capabilities
No declared permissions — minimal attack surface.
agent_memorydynamic_eval Is this flag fair?
Thanks — recorded.