speckit-review-simplify
Pass
Audited by Gen Agent Trust Hub on Jul 30, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTIONNO_CODE
Full Analysis
- [COMMAND_EXECUTION]: The skill directs the agent to locate and execute a local bash script at '.specify/scripts/bash/detect-changed-files.sh' with the '--json' flag to identify modified files for analysis.
- [PROMPT_INJECTION]: The skill exhibits an indirect prompt injection surface (Category 8) because it ingests and processes untrusted data from the user's project files.
- Ingestion points: Modified source code files and project configuration documents such as '.specify/memory/constitution.md', 'CLAUDE.md', and '.github/copilot-instructions.md'.
- Boundary markers: The skill does not define clear delimiters or provide instructions for the agent to ignore potentially malicious commands embedded within the analyzed files.
- Capability inventory: The skill utilizes shell script execution capabilities and suggests code modifications.
- Sanitization: There is no evidence of content validation or escaping of the data read from project files.
- [NO_CODE]: No executable files or scripts are bundled directly within the skill package; it relies on existing infrastructure within the user's project environment.
Audit Metadata