ml-rag-foundations
Pass
Audited by Gen Agent Trust Hub on Jun 25, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: No malicious patterns, obfuscation, or unauthorized behaviors were detected. The skill is purely educational and descriptive in nature.
- [SAFE]: The external library references (google-genai, sentence-transformers, chromadb) are well-known, legitimate packages within the AI development ecosystem.
- [SAFE]: The provided Python example follows security best practices for documentation by using placeholders for sensitive information (e.g., 'GEMINI_API_KEY') and local paths for data storage.
- [SAFE]: While the RAG architectural pattern described involves processing external data which can be a surface for indirect prompt injection, the skill is an educational template and does not contain any malicious logic or instructions to bypass safety guidelines.
Audit Metadata