openspec-continue-change
Pass
Audited by Gen Agent Trust Hub on Apr 4, 2026
Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill executes the
openspecCLI with arguments derived from the user or context, providing a functional interface for project management. - [EXTERNAL_DOWNLOADS]: The skill requires the installation of the
openspecCLI tool as an external dependency. - [PROMPT_INJECTION]: The skill exhibits an indirect prompt injection surface by consuming and acting on information from external project files and CLI outputs.
- Ingestion points: Data from
openspec instructionsoutput fields and project dependency files. - Boundary markers: Present; the instructions explicitly separate internal constraints from the generated artifact content.
- Capability inventory: File system write access and shell command execution.
- Sanitization: Relies on the AI following instructional boundaries when processing external inputs.
Audit Metadata