thermo-nuclear-review
Pass
Audited by Gen Agent Trust Hub on Jun 12, 2026
Risk Level: SAFEPROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [SAFE]: The skill provides structured instructions for a security audit, focusing on side effects, developer experience, and feature gates without malicious intent.
- [COMMAND_EXECUTION]: The instructions direct the agent to use 'gh' or 'glab' CLI tools to read PR/MR discussions. This is a standard and safe use of developer tooling for context gathering.
- [PROMPT_INJECTION]: The skill has an indirect prompt injection surface as it processes untrusted data from external sources.
- Ingestion points: Code diffs in the checked-out branch and pull request comments retrieved via 'gh' or 'glab' CLI (SKILL.md).
- Boundary markers: No explicit delimiters or boundary markers are defined in the instructions to isolate untrusted data from the system prompt.
- Capability inventory: The skill is restricted to read-only analysis and CLI interaction for data retrieval; it does not request file-writing or arbitrary network exfiltration capabilities.
- Sanitization: No explicit sanitization or filtering of external content is described in the prompt.
Audit Metadata