stream-chain
Pass
Audited by Gen Agent Trust Hub on Feb 28, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill consists entirely of Markdown documentation, CLI usage examples, and configuration templates. No Python, JavaScript, or shell scripts are included in the package.
- [SAFE]: No prompt injection patterns, hardcoded credentials, or suspicious network operations were identified. The prompts provided in the examples are standard development tasks such as code analysis and refactoring.
- [SAFE]: Although the skill describes a workflow where data flows between agents (a potential surface for indirect prompt injection), the documentation includes the use of boundary markers (e.g., 'Previous step output:') to help the model distinguish between context and instructions.
Audit Metadata