boundary-value-generator
Pass
Audited by Gen Agent Trust Hub on Oct 2, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill ingests untrusted data in the form of YAML input specifications to generate test code, which presents a surface for indirect prompt injection.
- Ingestion points: The YAML fields defined in Step 1, including
name,type,min,max,regex, andenum_values, are consumed by the agent and interpolated into code templates. - Boundary markers: There are no defined delimiters or specific instructions for the agent to distinguish between data and potential instructions within the YAML input.
- Capability inventory: The skill is capable of generating source code for multiple test frameworks, including pytest, Jest, Vitest, xUnit, and JUnit 5.
- Sanitization: The instructions do not specify any sanitization, validation, or escaping logic for the input fields before they are interpolated into the generated code snippets.
Audit Metadata