tdd-london-chicago
Pass
Audited by Gen Agent Trust Hub on Sep 18, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: No malicious patterns detected. The skill instructions focus on software development best practices, architectural comparison, and coordination of testing agents.
- [INDIRECT_PROMPT_INJECTION]: The skill describes agent-assisted TDD workflows that process external source code to generate unit tests.
- Ingestion points: Source code targets (e.g.,
src/domain/Order.ts) referenced in theTaskcoordination examples inSKILL.md. - Boundary markers: None specified in the provided task templates.
- Capability inventory: Utilizes internal agent coordination (
qe-test-generator,qe-test-implementer,qe-test-refactorer) to perform code analysis and generation. - Sanitization: Not mentioned in the procedural documentation.
- Note: This exposure is a standard functional surface for development-focused skills and represents the primary intended use case, posing no unique threat beyond inherent agent capabilities.
Audit Metadata