wild-frontend
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 design directions and references to generate frontend code artifacts. This ingestion of untrusted data to influence code generation constitutes an attack surface for indirect prompt injection. \n
- Ingestion points: The agent is instructed in SKILL.md to use external "direction and references" as constraints for the output. \n
- Capability inventory: The skill includes instructions for creating components, custom CSS, and interactions, which are then rendered as artifacts. \n
- Boundary markers: The instructions lack explicit boundary markers or warnings to disregard instructions that might be embedded within the creative brief data. \n
- Sanitization: No sanitization, filtering, or validation of the input data is performed before it is used to generate executable frontend code.
Audit Metadata