agent-ready-cli

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

• Third-party content exposure detected (medium risk: 0.30). In the agent-ready-cli runtime workflow, the user-triggered agent-ready scan {URL} (and subsequent get {id} for queued scans) causes outsider-authored free text from the scanned public site (e.g., titles/headings/llms.txt/AGENTS.md/messages) to be ingested and printed back by the CLI for summarization.

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

• Potentially malicious external URL detected (high risk: 0.90). The skill instructs running "npx agent-ready-scanner" which fetches and executes the npm package at runtime (the referenced package URL: https://www.npmjs.com/package/agent-ready-scanner), so remote code is fetched-and-run as part of normal operation.