implementation-review
Pass
Audited by Gen Agent Trust Hub on Sep 11, 2026
Risk Level: SAFENO_CODEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [COMMAND_EXECUTION]: The skill instructions involve executing verification adapters and focused checks within the assigned workspace. Evidence: SKILL.md describes inspecting canonical CLI help and running a focused check based on project profile requirements.
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and process code candidates and repository diffs, which creates a potential surface for indirect prompt injection from untrusted source code. Ingestion points: Candidate materialization and repository diffs mentioned in SKILL.md. Boundary markers: The skill does not define specific delimiters for untrusted content. Capability inventory: The skill can write to CODING_STANDARDS.md and execute verification tools as described in SKILL.md. Sanitization: No specific sanitization of the input code is specified.
- [NO_CODE]: No executable code files (scripts or binaries) are shipped with the skill; it consists entirely of markdown instructions and templates.
Audit Metadata