openspec-propose
Pass
Audited by Gen Agent Trust Hub on Mar 9, 2026
Risk Level: SAFECOMMAND_EXECUTION
Full Analysis
- [COMMAND_EXECUTION]: The skill executes local commands using the openspec CLI to manage the lifecycle of project changes and artifacts. This behavior is essential to its purpose and is clearly documented.
- [PROMPT_INJECTION]: The skill exhibits a surface for indirect prompt injection as it processes untrusted user input and structured instructions from the CLI tool. It implements mitigation by instructing the agent to treat this data as constraints rather than direct output content, providing a necessary boundary.
Audit Metadata