thermo-nuclear-code-quality-review
Pass
Audited by Gen Agent Trust Hub on Sep 21, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and analyze untrusted external data, specifically branch diffs and repository instructions, which could contain adversarial instructions.
- Ingestion points: The agent is instructed to read branch diffs and repository-specific instruction files during the audit process.
- Boundary markers: The prompt does not define clear delimiters or specific instructions to the agent to treat the code content solely as data and to ignore any commands embedded within it.
- Capability inventory: While intended for review, the agent operating the skill typically has access to file system modification and terminal execution capabilities.
- Sanitization: The skill lacks mechanisms to sanitize, filter, or validate the content of the code changes before they are processed by the language model.
Audit Metadata