Caveat verdict
agent-native-speaker
88
🟢 Trusted
No high-risk patterns surfaced by the deep scan — automated capability review, not behavioral proof.
Offers educational guidance on AI concepts and architecture explanation directly from the agent's source code or documentation, with no indication of risk.
⚠ Flagged for review — coarse, uncorroborated signal, not a confirmed exploit. Review the config yourself before installing.
Automated static analysis — not a human review. Caveat flags capabilities, not confirmed intent, and can produce false positives. Disagree with this verdict? Use Dispute below.
90
security
100
transparency
90
maintenance
Findings (1)
Pattern match medium
References agent memory files
references/hermes-agent-architecture-map.md · code · MEMORY.md
Permissions & capabilities
No declared permissions — minimal attack surface.
data_encoding Is this flag fair?
Thanks — recorded.