refactoring-patterns
Pass
Audited by Gen Agent Trust Hub on Mar 6, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill is designed to process external source code, which introduces a potential surface for indirect prompt injection where malicious instructions could be embedded in the code being refactored.
- Ingestion points: Source code files in directories such as
src/services/(as specified in the Agent Integration examples inSKILL.md). - Boundary markers: The skill does not define specific delimiters or instructions to ignore embedded commands within the files it analyzes.
- Capability inventory: The skill facilitates the execution of shell commands like
npm testandgit commit, and utilizes agent coordination throughFleetManagerandTaskabstractions. - Sanitization: No explicit sanitization of input file content is defined to prevent the AI from interpreting comments or string literals as instructions.
Audit Metadata