eva-learn
Pass
Audited by Gen Agent Trust Hub on Jul 6, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill utilizes relative pathing to reference local configuration files within the Eva project ecosystem, ensuring that it only operates on trusted, internal logic sources.
- [SAFE]: It implements defensive instructions that prevent the agent from proceeding with incompatible versions or hallucinating procedures when sources are missing.
- [SAFE]: File writing operations are explicitly limited to user-defined document folders, protecting the skill repository and system-level configurations from unauthorized modification.
Audit Metadata