openspec-explore
Pass
Audited by Gen Agent Trust Hub on Apr 22, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill executes
openspec list --jsonto retrieve project context. This is a legitimate use of the tool provided by the author to synchronize project state with the agent. - [PROMPT_INJECTION]: The skill processes data from codebase files and OpenSpec artifacts, which constitutes an indirect prompt injection surface. This is expected behavior for a tool designed to analyze project context.
- Ingestion points: Local source code files and OpenSpec markdown documents in the 'openspec/changes/' directory.
- Boundary markers: No specific delimiters or instructions to ignore embedded commands are used when reading these files.
- Capability inventory: File system read access and execution of the 'openspec' CLI.
- Sanitization: Content is ingested and discussed without explicit sanitization or filtering.
Audit Metadata