Caveat verdict

ia-agent-native-architecture

compound-eng-agent-native-architecture

88
🟢 Trusted
No high-risk patterns surfaced by the deep scan — automated capability review, not behavioral proof.

Design reference for agent-native architecture principles; purely educational content with no executable behavior, credentials, or network access.

⚠ 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.

40
security
70
transparency
70
maintenance

Findings (4)

Pattern match critical

Accesses sensitive system files

references/shared-workspace-architecture.md · code · /etc/passwd

Pattern match medium

References agent configuration files

references/agent-execution-patterns.md · code · AgentConfig

Pattern match medium

Instructs covert action — may act without user awareness

references/hooks-patterns.md · prose · downgraded · silently

Pattern match medium

Accesses system credential store

references/mobile-storage.md · prose · downgraded · Keychain

Permissions & capabilities

No declared permissions — minimal attack surface.

Is this flag fair?

Check another skill Browse the registry Auditing your own skills or configs? Use the API