tdd
Pass
Audited by Gen Agent Trust Hub on Oct 7, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill contains instructional markdown files and configuration metadata for TDD practices. All code examples (TypeScript) are for conceptual demonstration of testing and mocking strategies.
- [INDIRECT_PROMPT_INJECTION]: The skill instructs the agent to read
GLOSSARY.mdand ADRs from the codebase to align with project-specific terminology. This is an ingestion of untrusted data, but it is used for terminology alignment rather than execution, and no dangerous capabilities are invoked with this data within the skill. - [CREDENTIALS_UNSAFE]: A code snippet in
mocking.mddemonstrates a hard-to-mock pattern usingprocess.env.STRIPE_KEY. This is a best-practice placeholder for environment variables and does not represent a hardcoded credential leak.
Audit Metadata