distill
Pass
Audited by Gen Agent Trust Hub on Apr 16, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill facilitates the processing and modification of external codebase data, creating a potential surface for indirect prompt injection.
- Ingestion points: The skill gathers context from the existing thread or codebase (SKILL.md).
- Boundary markers: No explicit delimiters or delimiters are specified to isolate external code content from the agent's core instructions.
- Capability inventory: The agent is instructed to modify the codebase by removing unused code, flattening component trees, and consolidating styles (SKILL.md).
- Sanitization: The skill lacks explicit sanitization steps for ingested code, relying instead on the AskUserQuestionTool to resolve low-confidence scenarios and instructions to preserve necessary functionality.
Audit Metadata