pinecone

Pass

Audited by Gen Agent Trust Hub on Mar 29, 2026

Risk Level: SAFE
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill documentation includes instructions to install and use official client libraries (@pinecone-database/pinecone and openai) from standard registries. These are associated with well-known technology services.
  • [PROMPT_INJECTION]: The skill provides implementation templates for a Retrieval-Augmented Generation (RAG) pattern, which creates an indirect prompt injection surface.
  • Ingestion points: Data is ingested via the Pinecone metadata field (match.metadata?.text) in the ragQuery function within SKILL.md.
  • Boundary markers: The provided prompt template uses a basic header structure (Answer based on this context:\n\n) to separate context from the user question.
  • Capability inventory: The skill facilitates API calls to vector database and language model providers to process data and generate outputs.
  • Sanitization: The examples do not demonstrate specific sanitization or validation of the retrieved content before interpolation into the prompt.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 29, 2026, 07:53 AM
Security Audit — agent-trust-hub — pinecone