codebase-cleanup-refactor-clean
Pass
Audited by Gen Agent Trust Hub on Feb 17, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- Indirect Prompt Injection (LOW): The skill is designed to ingest and process external code provided by the user via the
$ARGUMENTSplaceholder. This creates a surface for indirect prompt injection where instructions hidden within code comments or data could attempt to manipulate the agent's behavior. - Ingestion points: Code provided through
$ARGUMENTSand user-supplied codebase context. - Boundary markers: Absent. The instructions do not specify delimiters or warnings to ignore instructions embedded within the code being refactored.
- Capability inventory: No executable scripts or tool-calling capabilities are defined within this specific skill file.
- Sanitization: None. The skill assumes the provided code is passive data for analysis.
Audit Metadata