skills/terminalskills/skills/pinecone/Gen Agent Trust Hub

pinecone

Pass

Audited by Gen Agent Trust Hub on Mar 13, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill installs official client libraries for Pinecone ('@pinecone-database/pinecone', 'pinecone-client') and OpenAI ('openai') from standard package registries. These are verified well-known services.
  • [PROMPT_INJECTION]: The RAG pipeline in 'rag.js' presents an indirect prompt injection surface.
  • Ingestion points: Data retrieved from the vector database via 'index.query' is directly included in the LLM prompt.
  • Boundary markers: The implementation lacks delimiters or instructions to ignore embedded commands within the retrieved context.
  • Capability inventory: The skill provides full index management and vector operations.
  • Sanitization: There is no evidence of content sanitization or validation for the retrieved metadata before it is interpolated into the system prompt.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 13, 2026, 09:16 PM