code-simplification
Pass
Audited by Gen Agent Trust Hub on Sep 29, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill facilitates the processing and modification of external source code, creating a surface for potential indirect prompt injection attacks.
- Ingestion points: Source code provided to the agent for refactoring, analysis, or review (SKILL.md, references/language-patterns.md).
- Boundary markers: The instructions lack explicit delimitation or warnings to ignore instructions that might be embedded within the source code.
- Capability inventory: The refactoring process involves the agent's file system modification capabilities and mentions the use of command-line tools like
sedorjscodeshiftfor large-scale transformations (SKILL.md). - Sanitization: There are no specified mechanisms for sanitizing or validating the input code.
Audit Metadata