tdd
Pass
Audited by Gen Agent Trust Hub on Oct 9, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill instructs the agent to process user-provided specifications and existing code to guide development, establishing a surface for indirect prompt injection. This behavior is inherent to the skill's primary purpose as a development tool.
- Ingestion points: The workflow in
SKILL.mddirects the agent to infer requested behavior from user specifications and existing source code. - Boundary markers: No specific delimiters or safety instructions for distinguishing untrusted input from system instructions are provided in the skill files.
- Capability inventory: The agent is expected to write files and execute tests as part of the TDD loop.
- Sanitization: No sanitization or validation of input data is mentioned.
Audit Metadata