openspec-propose
Pass
Audited by Gen Agent Trust Hub on Sep 20, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill implements a strictly bounded planning workflow using the
openspecCLI. It includes explicit guardrails that prevent the agent from modifying project source code or beginning implementation until explicitly authorized in a separate workflow. All tool invocations are restricted to theopenspecnamespace via theallowed-toolsconfiguration.
Audit Metadata