form-ux
Pass
Audited by Gen Agent Trust Hub on Oct 22, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill analyzes external content such as form goals, rules, and existing markup provided in the user context.
- Ingestion points: Inputs defined in
contract.jsoninclude form goals, fields, validation rules, and existing markup. - Boundary markers: No specific delimiters or instructions to ignore embedded content were identified in the prompt instructions.
- Capability inventory: The skill is restricted to generating text-based UX analysis and evidence tables; no tool usage, file system access, or network operations are requested in the instructions.
- Sanitization: No specific sanitization, validation, or escaping of the input data is described before it is processed by the model.
- [SAFE]: The skill instructions promote secure handling of sensitive data by requiring the model to identify fields that are personal or financial and specifying they must never be persisted locally.
Audit Metadata