speckit-review-errors
Pass
Audited by Gen Agent Trust Hub on Jul 30, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill mandates the execution of a specific local shell script at
.specify/scripts/bash/detect-changed-files.shto identify target files for analysis. - [PROMPT_INJECTION]: The skill exhibits an indirect prompt injection surface as it ingests and processes content from external files (code reviews) without utilizing delimiters, boundary markers, or specific instructions to the agent to disregard instructions embedded in the data. Mandatory Evidence Chain: 1. Ingestion points: Content of changed files processed during the review phase. 2. Boundary markers: Absent. 3. Capability inventory: Local script execution via bash. 4. Sanitization: Absent.
Audit Metadata