variant
Pass
Audited by Gen Agent Trust Hub on Oct 5, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to process user-provided UI descriptions and translate them into functional code variants, creating an attack surface where malicious instructions could be embedded in the design brief.
- Ingestion points: The agent takes a "described piece of UI" as the primary input for its generation process (SKILL.md, Section 1).
- Boundary markers: The instructions do not specify any delimiters or safety markers to differentiate between the user's UI description and the agent's internal logic.
- Capability inventory: The skill instructs the agent to generate HTML and CSS code and host it within a "real page" or a self-contained file (SKILL.md, Section 4).
- Sanitization: There are no requirements for input validation, sanitization, or escaping of the user-provided descriptions before they are interpolated into the code generation task.
Audit Metadata