geo-action-plan

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

• Third-party content exposure detected (high risk: 0.85). The required workflow calls multiple Promptwatch MCP tools (e.g., list_projects, get_visibility_time_series, get_content_gap_stats, get_citations, get_competitor_heatmap) which at runtime fetch and return outsider-authored web/marketplace/citation/crawler/traffic text/data into the agent’s LLM context via the MCP server responses.