TDD Expert
Pass
Audited by Gen Agent Trust Hub on Sep 12, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted user-provided requirements and behavior descriptions to generate code and tests, which presents a surface for potential injection if malicious instructions are embedded in the user's input.
- Ingestion points: User-provided inputs regarding functionality, interfaces, and edge cases described in the 'Operating procedure' section.
- Boundary markers: None present to distinguish user-provided data from system instructions.
- Capability inventory: The skill instructs the agent to 'Produce the test list, then the code and tests', which involves file system writes and test execution capabilities within the agent environment.
- Sanitization: No sanitization or validation of the provided requirements is specified.
Audit Metadata