code-review
Pass
Audited by Gen Agent Trust Hub on Nov 6, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted data from target source files, Architectural Decision Records (ADRs), and project documentation, creating a surface for indirect prompt injection.
- Ingestion points: Target code files and project-specific documentation are read into the context (SKILL.md).
- Boundary markers: The instructions do not define explicit delimiters or instructions to ignore commands embedded in the processed code.
- Capability inventory: The skill utilizes Bash for shell command execution and the Task tool for spawning additional agent sessions (engine-specialists, qa-tester).
- Sanitization: There is no sanitization or validation of the content within the ingested files.
Audit Metadata