thermo-nuclear-code-quality-review
Pass
Audited by Gen Agent Trust Hub on Jul 14, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill consists entirely of natural language instructions for the agent to follow when reviewing code for maintainability and design quality.
- [PROMPT_INJECTION]: While the skill uses strong instructional language (‘Non-Negotiable Additional Standards’, ‘Above all’) to establish a strict persona, it does not attempt to bypass core safety guardrails or leak internal system prompts.
- [REMOTE_CODE_EXECUTION]: No external dependencies, remote script fetching, or code execution patterns are present.
- [DATA_EXFILTRATION]: The skill does not perform network operations or access sensitive local files. The ‘disable-model-invocation: true’ setting in the frontmatter further restricts the agent from using tools that could perform such actions.
- [COMMAND_EXECUTION]: There are no shell commands, subprocess calls, or dynamic execution patterns (‘eval’, ‘exec’) within the skill content.
Audit Metadata