ts-workflow-prototype
Pass
Audited by Gen Agent Trust Hub on Aug 4, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill defines a structured methodology for managing sub-agents and artifacts (design docs, plans, reviews). All operations are local to the repository and follow standard development practices.
- [SAFE]: No network exfiltration, hardcoded credentials, or suspicious remote code downloads were detected. The skill references external model names (e.g., OpenAI sol, Anthropic fable) as part of a configuration for sub-agent selection, which is a common pattern for multi-agent workflows.
- [SAFE]: The use of sub-agents is managed through a 'Core Contract' that emphasizes self-contained prompts and fresh contexts, reducing the risk of accidental data leakage from parent history.
- [SAFE]: The skill does not attempt to bypass safety filters or provide instructions to override its own constraints.
Audit Metadata