wireframe
Pass
Audited by Gen Agent Trust Hub on Sep 16, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes user-supplied task names to derive file slugs and generates content based on user interviews. While this creates a surface for indirect prompt injection where malicious input could attempt to influence the agent's behavior, the skill's capabilities are restricted to writing static design files in a localized directory, which effectively mitigates risk.
- Ingestion points: User-provided task names and interview responses (SKILL.md).
- Boundary markers: None explicitly defined.
- Capability inventory: Writing mockup files to the
./opendesign/mockups/directory (SKILL.md). - Sanitization: The skill instructs the agent to derive a slug from the task name, which acts as a basic form of input normalization.
Audit Metadata