openspec-explore
Pass
Audited by Gen Agent Trust Hub on Mar 9, 2026
Risk Level: SAFE
Full Analysis
- [COMMAND_EXECUTION]: Executes the 'openspec' command-line tool with the 'list --json' argument to retrieve project metadata and status of active changes.
- [SAFE]: Accesses local documentation files such as 'proposal.md' and 'design.md' to provide context-aware suggestions. Operations are restricted to the local environment with no external network activity or unauthorized file access.
- [PROMPT_INJECTION]: The skill includes explicit behavioral constraints that prevent the agent from performing code implementation tasks, effectively limiting the operational scope to analysis and documentation.
Audit Metadata