refactoring-specialist
Pass
Audited by Gen Agent Trust Hub on Oct 22, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill analyzes and refactors code from the project context, creating a surface where malicious instructions embedded in source files could attempt to influence the agent.
- Ingestion points: The skill queries the context manager for code quality issues and reviews code structure (SKILL.md).
- Boundary markers: Absent. The instructions do not specify delimiters or provide warnings to the agent to ignore instructions embedded within the code being refactored.
- Capability inventory: The skill is authorized to implement systematic refactoring and update documentation, which involves file modification capabilities.
- Sanitization: Absent. There are no mechanisms described for sanitizing or validating ingested code before it is processed by the agent.
Audit Metadata