openspec-propose
Pass
Audited by Gen Agent Trust Hub on Mar 9, 2026
Risk Level: SAFE
Full Analysis
- [COMMAND_EXECUTION]: The skill utilizes the
openspecCLI to manage change sets and generate artifacts. Commands such asopenspec new,openspec status, andopenspec instructionsare used as intended for the skill's primary purpose. - [PROMPT_INJECTION]: The instructions provided to the AI agent focus on task execution and data processing. No patterns attempting to bypass safety filters or override system-level instructions were found.
- [DATA_EXFILTRATION]: No evidence was found of sensitive data access or unauthorized network transmissions. The skill's operations are confined to the local
openspec/changes/directory.
Audit Metadata