thermo-nuclear-code-quality-review
Pass
Audited by Gen Agent Trust Hub on Oct 11, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and analyze untrusted external data, which creates a potential surface for indirect prompt injection attacks.
- Ingestion points: The skill processes external content through the
diffScope(which contains code diffs and file changes) andexistingRootDoc(which includes agent instruction files likeCLAUDE.md). - Boundary markers: There are no instructions for the agent to use specific delimiters or protective wrappers when processing the code diffs to prevent the agent from accidentally executing instructions hidden within the code comments or content.
- Capability inventory: The skill requires file-reading capabilities to evaluate the code changes and generates descriptive output (remedies and finding tables) based on the processed untrusted data.
- Sanitization: The skill does not implement any validation, filtering, or escaping of the input data to detect or neutralize potential injection attempts.
Audit Metadata