express-intent-in-code

Pass

Audited by Gen Agent Trust Hub on Oct 3, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [SAFE]: The skill provides instructions for standard code quality improvements and refactoring patterns focused on readability and type safety.
  • [INDIRECT_PROMPT_INJECTION]: The skill ingests 'supplied code' (ingestion point) and has capabilities for 'file-write' and 'command execution' (lint, type check, and behavior checks). The instructions do not define 'boundary markers' or 'sanitization' for these inputs, but operations are restricted to 'authorized code'.
Audit Metadata
Risk Level
SAFE
Analyzed
Oct 3, 2026, 12:56 PM