openspec-explore
Pass
Audited by Gen Agent Trust Hub on Sep 20, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill interacts with the
openspecCLI to manage project metadata, changes, and documentation. It uses restricted shell access to perform these tasks. - [INDIRECT_PROMPT_INJECTION]: The skill processes project configuration and codebase files to inform its exploration logic. This is a standard functional surface for tools that analyze existing code, where content within those files could potentially influence the agent's reasoning.
- Ingestion points: Codebase files and project-specific configuration files (openspec/config.yaml).
- Boundary markers: No specific delimiters or safety instructions are defined for processing external data.
- Capability inventory: The skill is permitted to run openspec commands and write markdown artifacts to the file system.
- Sanitization: No explicit sanitization or validation of the ingested file content is performed.
Audit Metadata