thermo-nuclear-code-quality-review
Pass
Audited by Gen Agent Trust Hub on Oct 10, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted external data (git diffs and source code contents) which could potentially contain malicious instructions intended to manipulate the agent's review output or behavior.
- Ingestion points: Untrusted content is ingested via the
### Git / diff outputand### Changed file contentssections defined in the subagent reference file. - Boundary markers: The skill uses markdown headers to separate the rubric instructions from the external code data, providing basic logical separation.
- Capability inventory: The skill is restricted to generating text-based review comments; it does not include tool definitions, network access, or file system write capabilities.
- Sanitization: The instructions do not specify any sanitization, filtering, or escaping mechanisms for the ingested code content.
Audit Metadata