vector-setup

MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).

• Third-party content exposure detected (high risk: 0.80). The SKILL.md explicitly instructs running npm install and npx commands (e.g., "npm install ruvector@0.2.25" and related add-ons in Steps 1–3 and using npx in Steps 3–5), which fetch and execute packages from the public npm registry (untrusted third‑party code) that the agent will install/run and that can influence subsequent tool behavior.

MEDIUM W012: Unverifiable external dependency detected (runtime URL that controls agent).

• Potentially malicious external URL detected (high risk: 0.90). The skill runs npm/npx at runtime to fetch and execute packages (notably ruvector@0.2.25 and add-ons such as ruvector-onnx-embeddings-wasm, @ruvector/pi-brain, @ruvector/ruvllm) from the npm registry (e.g. https://www.npmjs.com/package/ruvector), so remote code is fetched and executed and is required for the skill to function.