constructive-safegres
Pass
Audited by Gen Agent Trust Hub on Feb 28, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill is a documentation-only resource providing instructions for the AI on how to interpret and generate Safegres authorization policies.
- [SAFE]: No executable code, shell commands, or network operations are present in the skill content.
- [SAFE]: References to the @constructive-io/sdk package are consistent with the skill author constructive-io and represent legitimate vendor-owned resource patterns.
- [SAFE]: The skill includes defensive documentation and adversarial warnings, specifically highlighting the risks of AuthzAllowAll and unbound membership checks.
Audit Metadata