ui-prompt-generator
Pass
Audited by Gen Agent Trust Hub on Sep 28, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONNO_CODE
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes external data from Product-Spec.md, creating a surface for indirect instructions.
- Ingestion points: The workflow relies on reading the contents of Product-Spec.md to define UI requirements.
- Boundary markers: Absent. There are no instructions providing delimiters or warnings to ignore embedded instructions within the specification file.
- Capability inventory: The skill is limited to text generation and writing results to UI-Prompts.md. No high-privilege capabilities such as network access, command execution, or system modification are requested or used.
- Sanitization: The instructions do not define any validation or sanitization logic for the data extracted from the source document.
Audit Metadata