strict-quality-review
Pass
Audited by Gen Agent Trust Hub on Jun 16, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection because it processes untrusted external data (git diffs and commit ranges) without sufficient safeguards.
- Ingestion points: The Adversarial Review Workflow in SKILL.md defines the review scope as branch diffs or user-specified file ranges.
- Boundary markers: No specific delimiters or instructions to ignore embedded commands within the diff content are provided, potentially allowing instructions hidden in code comments to influence the agent.
- Capability inventory: The skill instructions state the agent 'synthesizes findings and applies accepted changes,' indicating a filesystem write capability that could be abused via a successful injection.
- Sanitization: No input validation or sanitization logic is described for the analyzed code content.
Audit Metadata