agent-deck

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

• Third-party content exposure detected (high risk: 0.80). The skill explicitly recommends and attaches MCP servers for web search (e.g., "exa", "firecrawl") and shows an example launching a "Researcher" sub-agent to "find information about latest trends in AI", which indicates the agent will fetch and read untrusted public web content as part of its workflow.