design-exploration
Pass
Audited by Gen Agent Trust Hub on Oct 22, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill instructs the agent to analyze external source code and context, which acts as a surface for indirect prompt injection if the analyzed files contain malicious instructions.
- Ingestion points: Selected component source code, parent layout, route structure, dependencies, and styles (SKILL.md).
- Boundary markers: No specific delimiters or "ignore instructions" warnings are defined for the agent to use when processing the code content.
- Capability inventory: The skill involves reading files and delegating tasks to a subagent based on the analyzed content.
- Sanitization: The skill lacks instructions for sanitizing or escaping content found within the analyzed source code before including it in the design brief reasoning process.
Audit Metadata