Pinecone Search

Pinecone vector search and document upload tool for knowledge base management

This skill appears to implement Pinecone uploads and search as described, but take these precautions before installing or using it: - The runtime requires PINECONE_API_KEY, EMBEDDING_API_KEY and EMBEDDING_BASE_URL (the registry metadata omitted these) — set and protect these keys carefully. - The tool records and returns absolute file paths (the 'source' field) and other metadata in JSON and stores them in Pinecone metadata; review whether you want full paths and file-level metadata indexed or returned to callers. - Ensure EMBEDDING_BASE_URL points to a trusted embedding provider (e.g., OpenAI). If you set this to an untrusted endpoint it will receive file contents and your EMBEDDING_API_KEY. - Use the provided --dry-run option first to preview which files and how many chunks will be processed before uploading anything. - Consider running the tool in an isolated environment (or with least-privilege keys) and inspect the code (pinecone_tool.py, upload.py, search.py) yourself if you have sensitive documents. - If you need the skill listed in a registry, ask the publisher to correct the registry metadata so required environment variables and secrets are clearly declared. If you want, I can point out the exact lines that send file paths/metadata to Pinecone and where the embedding base URL and keys are used so you can audit or modify them.

Type: OpenClaw Skill Name: pinecone-search Version: 0.1.3 The `pinecone-search` skill bundle is a legitimate tool for managing vector databases. It provides functionality for loading, splitting, and uploading Markdown and TXT documents to Pinecone, as well as performing hybrid (vector + BM25) searches. The implementation in `pinecone_tool.py`, `upload.py`, and `search.py` is well-structured, uses standard libraries like `openai` and `pinecone`, and adheres to its stated purpose without any indicators of data exfiltration, malicious execution, or prompt injection.