Voyage AI CLI

Voyage AI embedding and reranking CLI integrated with MongoDB Atlas Vector Search. Use for: generating text embeddings, reranking search results, storing embeddings in Atlas, performing vector similarity search, creating vector search indexes, listing available models, comparing text similarity, bulk ingestion, interactive demos, and learning about AI concepts. Triggers: embed text, generate embeddings, vector search, rerank documents, voyage ai, semantic search, similarity search, store embeddings, atlas vector search, embedding models, cosine similarity, bulk ingest, explain embeddings.

This skill is a coherent CLI wrapper for Voyage AI + MongoDB Atlas Vector Search, but check a few things before installing: 1) The package installs globally via npm — verify the 'voyageai-cli' package and its maintainer (npm listing and GitHub repo) so you trust what code will be run on your machine. 2) You must provide VOYAGE_API_KEY; the SKILL.md also references MONGODB_URI for DB operations but that env var is not declared — only set MONGODB_URI when you intend to allow the CLI to connect to your Atlas cluster. 3) The CLI can persist an API key via 'vai config', which writes to your home directory; prefer least-privilege API keys and consider using ephemeral or scoped credentials. 4) The README instructs adding shell completion to ~/.bashrc or zsh completion directories — these modify your shell config. 5) If you need higher assurance, inspect the npm package code (postinstall scripts, config storage location) or run the CLI in an isolated environment (container or separate account) before giving it production credentials.

Type: OpenClaw Skill Name: voyageai-skill Version: 1.4.0 The skill is classified as suspicious due to its installation method and system modifications. It requires a global npm package installation (`npm install -g voyageai-cli`) and includes instructions to modify the user's shell configuration (`~/.bashrc`) for shell completions, both found in `SKILL.md`. While these actions are common for CLI tools and are for a stated, legitimate purpose, they involve high-privilege operations that could be leveraged for unintended system changes or persistence if the underlying package were compromised or the agent were prompted maliciously.