thermo-nuclear-code-quality-review
Pass
Audited by Gen Agent Trust Hub on Jun 19, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill instructs the agent to gather the review scope using standard git commands such as
git rev-parseandgit diff. These are benign operations necessary for the skill's functional goal of reviewing code changes.\n- [PROMPT_INJECTION]: The skill processes untrusted external data (the code and diffs being reviewed), which is an inherent surface for indirect prompt injection. This risk is common for code review tools and is documented here as part of the analysis.\n - Ingestion points: Git diff output and full contents of modified files in the repository (SKILL.md).\n
- Boundary markers: Absent; the skill provides a rubric for analysis but does not define explicit delimiters or 'ignore' instructions for the code content itself.\n
- Capability inventory: Shell execution of git commands and file system read access.\n
- Sanitization: Not specified; the skill relies on the underlying agent's standard safety protocols and the
disable-model-invocation: truesetting to limit potential exploit impact.
Audit Metadata