mcp-gethookd

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

• Third-party content exposure detected (high risk: 0.85). Outsider free text can enter the agent via the GetHookd MCP tools (search_ads, get_ad, get_top_ads, get_brand_spy, etc.), which retrieve competitor ad/brand content authored by third parties from a public ad library at runtime and then pass that readable text into the LLM for synthesis.