requesting-code-review
Pass
Audited by Gen Agent Trust Hub on May 31, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection because it incorporates untrusted data from git diffs and source code into the subagent's context.
- Ingestion points: Git diff output and source code content enter the agent context in the reviewer template (references/code-reviewer-template.md).
- Boundary markers: The skill uses markdown headers as delimiters but lacks specific instructions to ignore adversarial text within the code diffs.
- Capability inventory: The subagent performs code quality assessments and provides recommendations on production readiness.
- Sanitization: No sanitization or escaping of the code content is performed before it is processed by the agent.
Audit Metadata