agent-ready-mcp

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

• Third-party content exposure detected (high risk: 0.85). The required runtime workflow uses the MCP tools scan_site/get_scan, whose tool results include “scraped text from the target site (titles, headings, llms.txt / AGENTS.md bodies…)”; that is outsider-authored free text from a user-supplied URL that the agent ingests into the LLM context as tool output.

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

• Potentially malicious external URL detected (high risk: 0.90). The skill requires running "npx -y agent-ready-mcp@latest", which fetches and executes code from the npm package (https://www.npmjs.com/package/agent-ready-mcp) at runtime, so it relies on external content that is executed locally.