pinecone-query

Pass

Audited by Gen Agent Trust Hub on Sep 15, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill provides instructions for interacting with the Pinecone vector database. It correctly advises users to store the PINECONE_API_KEY as an environment variable, which is a standard and safe practice for credential management.
  • [EXTERNAL_DOWNLOADS]: The skill references the official Pinecone website (pinecone.io) for documentation and sign-up, which is a well-known and trusted service. This does not escalate the security verdict.
  • [COMMAND_EXECUTION]: The skill uses specific MCP tools (list-indexes, search-records, describe-index) intended for its purpose. It does not perform arbitrary command execution or access sensitive local files.
  • [INDIRECT_PROMPT_INJECTION]: While the skill processes user-provided search queries (untrusted input), it does so by passing them to a specific search tool. The potential for prompt injection is low and mitigated by the limited scope of the tool's capabilities.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 15, 2026, 10:20 PM
Security Audit — agent-trust-hub — pinecone-query