Embeddings
Pass
Audited by Gen Agent Trust Hub on Apr 20, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill contains technical documentation and standard code snippets for working with vector embeddings.
- [EXTERNAL_DOWNLOADS]: The skill references several standard industry libraries including LangChain, OpenAI, Cohere, Voyage AI, and various vector database clients (Pinecone, Qdrant, ChromaDB, etc.). These are well-known, established tools for the described use case.
- [DATA_EXFILTRATION]: While the skill involves sending data to external embedding providers (OpenAI, Cohere, etc.), this is the primary intended function of the skill and uses standard API integration patterns with no evidence of unauthorized exfiltration.
Audit Metadata