eve-agent-native-design
Pass
Audited by Gen Agent Trust Hub on Sep 16, 2026
Risk Level: SAFENO_CODE
Full Analysis
- [NO_CODE]: The skill package contains only Markdown documentation files (SKILL.md and references/eve-horizon-primitives.md). There are no executable scripts, binaries, or active code components present.
- [SAFE]: The content provides architectural principles (Parity, Granularity, Composability, Emergent Capability) and references platform primitives. While it mentions security-sensitive CLI commands such as
eve auth mintandeve secrets set, these are documented as standard platform features for legitimate authentication and secret management within the Eve Horizon ecosystem. No patterns of credential exfiltration, prompt injection, or obfuscation were detected.
Audit Metadata