ts-implement
Pass
Audited by Gen Agent Trust Hub on Aug 4, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill establishes a robust judge-worker workflow for code implementation, emphasizing verification (linting, typechecking, testing) and documentation.
- [SAFE]: Security is explicitly integrated into the workflow; instructions command the agent to identify unsafe task inputs and evaluate security invariants, failure modes, and domain rules during the change application phase.
- [SAFE]: External references are limited to related skills within the same developer ecosystem (ts-principles, ts-technical-writing, ts-log), posing no external supply chain or exfiltration risks.
- [PROMPT_INJECTION]: The skill defines a surface for indirect prompt injection by processing external task inputs (requests, plans, designs). However, the instructions specifically mitigate this by requiring the agent to identify and exclude 'unsafe' findings, maintaining a safe posture.
Audit Metadata