competitive-intelligence

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

• Third-party content exposure detected (high risk: 1.00). The skill's required workflow explicitly instructs web research of public sources (see "Phase 2: Research Your Company" and "Phase 3: Research Each Competitor" which pull product pages, blogs, release notes, and user reviews like "G2 OR Capterra"), so the agent will ingest untrusted, user-generated third-party content and use it to drive analysis and actions.