together-local-dev-loop
Pass
Audited by Gen Agent Trust Hub on Sep 10, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill implements security best practices by instructing the agent to never save live credentials or sensitive outputs as fixtures. It emphasizes reading the
TOGETHER_API_KEYfrom an approved secret store and replacing any sensitive text with synthetic data. - [EXTERNAL_DOWNLOADS]: The skill references official Together AI documentation and their public GitHub repository for the Python SDK. These are well-known technology services and official resources, representing safe external references for integration development.
- [INDIRECT_PROMPT_INJECTION]: The skill fetches response shapes and error codes from official API documentation. While this is an ingestion point for external data, the source is a well-known service and the instructions focus on structural validation of code, posing no significant security risk.
Audit Metadata