thermo-nuclear-code-quality-review
Pass
Audited by Gen Agent Trust Hub on Sep 6, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [SAFE]: The skill consists of natural language instructions guiding an AI agent to perform code reviews. No malicious code, obfuscation, or unauthorized access patterns were detected.
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to analyze external code changes (untrusted data), which constitutes an indirect prompt injection surface. However, the skill lacks tool capabilities to execute code or perform network operations, and the platform configuration restricts model invocation, making the risk negligible. 1. Ingestion points: Instructions in SKILL.md direct the agent to audit current branch changes. 2. Boundary markers: Absent. 3. Capability inventory: No scripts or tool usage found in SKILL.md; agent is limited to text generation. 4. Sanitization: Absent.
Audit Metadata