aidlc-code-review
Pass
Audited by Gen Agent Trust Hub on Jul 20, 2026
Risk Level: SAFEPROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [PROMPT_INJECTION]: The skill analyzes external content such as source code and design documents, which presents a surface for indirect prompt injection.
- Ingestion points: Reads source files, design documents, tasks.md, and git diff output (SKILL.md, actions/review.md).
- Boundary markers: None; the skill does not use specific delimiters or instructions to ignore embedded commands in the analyzed files.
- Capability inventory: Performs file system writes (reports and backups) and executes shell commands (test suites) (actions/apply-fixes.md).
- Sanitization: There is no mention of sanitizing or escaping the content read from files before it is processed by the agent.
- [COMMAND_EXECUTION]: The skill executes the project's test suite locally during the fix application phase.
- Evidence: In actions/apply-fixes.md, the skill is instructed to "Verify the fix doesn't break existing tests (run test suite)" which involves executing code within the user's environment.
Audit Metadata