frontend-ui-workflow
Pass
Audited by Gen Agent Trust Hub on Oct 24, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to process untrusted external data to drive its code generation workflow.
- Ingestion points: According to
SKILL.md, the workflow ingests user tasks, external requirements, design files, and existing feature specifications. - Boundary markers: No explicit delimiters or instructions are provided to the agent to isolate untrusted input from the workflow's core instructions.
- Capability inventory: The skill has broad capabilities to read from and write to the local file system, including creating new components, hooks, and project documentation as seen in
references/ui-generation.mdandreferences/clean-implementation.md. - Sanitization: There is no mention of sanitizing or escaping content from external requirements before it is used to influence the generation of frontend code.
Audit Metadata