agent-ready-cli

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

• Third-party content exposure detected (high risk: 0.85). The required runtime workflow for scan/get/list sends the user-supplied URL to the hosted agent-ready REST API, which fetches and analyzes that public page content; that fetched outsider page text is then used to produce the scan result that the agent reads/relays into the LLM context (indirect prompt injection risk via scanned web content).

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

• Potentially malicious external URL detected (high risk: 0.80). The skill explicitly instructs running "npx agent-ready-scanner" which fetches and executes remote code from the npm package (https://www.npmjs.com/package/agent-ready-scanner) at runtime, so that npm URL is a runtime dependency that executes remote code.