tui-form
Pass
Audited by Gen Agent Trust Hub on Oct 7, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted data via form field labels, values, and error messages provided in the input model.
- Ingestion points: The skill takes external strings from the input model fields and submitLabel and interpolates them into the final TUI and JSON outputs.
- Boundary markers: There are no explicit delimiters or system-level instructions provided to the agent to prevent it from obeying commands that might be embedded in user-supplied form fields.
- Capability inventory: The skill is restricted to text generation and does not have access to file system tools, network operations, or shell execution.
- Sanitization: The skill does not include any mechanisms for sanitizing or escaping user-provided text to mitigate prompt injection risks.
Audit Metadata