research-agent

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

• Third-party content exposure detected (high risk: 1.00). The SKILL.md explicitly instructs the agent to fetch and scrape external public content using MCP tools—e.g., Perplexity for best-practices searches and Firecrawl via scripts/mcp/firecrawl_scrape.py with an arbitrary --url—so the agent will read and act on untrusted third-party web content.