competitor-monitoring

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

• Third-party content exposure detected (high risk: 0.90). The skill explicitly instructs the agent to fetch and scan public competitor sources—pricing pages, changelogs, job postings, blogs, social media, and review sites like G2/Capterra/Crunchbase—which are untrusted third-party content that the agent must read and interpret to produce threat assessments and recommended actions.