code-simplifier
Pass
Audited by Gen Agent Trust Hub on Sep 15, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill operates by analyzing and refactoring user-provided source code, which constitutes an inherent surface for indirect prompt injection attacks.
- Ingestion points: Untrusted source code provided for simplification, which is the primary data source for all 45 rules defined in the references directory.
- Boundary markers: The skill's instructions do not specify the use of delimiters or provide the agent with directives to ignore instructions that may be embedded within the source code it processes.
- Capability inventory: The AI agent implementing these simplification rules typically has access to the local file system and the ability to execute terminal commands.
- Sanitization: There are no provisions or instructions within the skill for sanitizing, validating, or escaping the content of the processed code before it is analyzed or modified.
Audit Metadata