thermo-nuclear-code-quality-review

Pass

Audited by Gen Agent Trust Hub on Aug 29, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill is designed to process external, untrusted data (source code changes) which could contain malicious instructions intended to influence the agent's behavior.
  • Ingestion points: The skill instructs the agent to analyze the "current branch's changes" within the codebase (SKILL.md).
  • Boundary markers: There are no explicit instructions for the agent to use delimiters or ignore embedded instructions when reading the code changes.
  • Capability inventory: The skill encourages the agent to propose significant code restructurings and refactors, which involves generating and potentially applying large blocks of code.
  • Sanitization: The skill lacks any instructions for sanitizing or filtering input from the source code being reviewed.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 29, 2026, 12:38 PM
Security Audit — agent-trust-hub — thermo-nuclear-code-quality-review