thermo-nuclear-code-quality-review
Pass
Audited by Gen Agent Trust Hub on Oct 20, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes external data in the form of code changes and branch diffs, which acts as a vector for untrusted instructions.
- Ingestion points: The agent is instructed to perform a deep code quality audit of the current branch's changes (SKILL.md).
- Boundary markers: There are no specific instructions or delimiters provided to help the agent distinguish its internal logic from instructions that might be embedded in the code being reviewed (e.g., in code comments).
- Capability inventory: The skill is intended to read files and generate descriptive feedback/review comments.
- Sanitization: The instructions do not include any logic for sanitizing, escaping, or filtering the external code content before interpolation into the agent's context.
Audit Metadata