distill
Pass
Audited by Gen Agent Trust Hub on Oct 6, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill analyzes external design context and codebases to identify and remove complexity, which introduces a surface for indirect prompt injection where instructions could be hidden in the data being processed.
- Ingestion points: The skill ingests the user's codebase and design context during the 'Assess Current State' phase.
- Boundary markers: There are no explicit boundary markers or 'ignore embedded instructions' warnings defined to separate ingested data from the skill's logic.
- Capability inventory: The skill possesses file modification and deletion capabilities as described in the 'Code Simplification' section (removing unused code and orphaned files).
- Sanitization: No sanitization, validation, or filtering of the external code or design content is specified before the agent processes it.
Audit Metadata