competitive-intelligence

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

• Third-party content exposure detected (high risk: 0.90). The skill's required "Phase 1: Intelligence Collection" workflow explicitly directs automated monitoring and ingestion of open/public third-party sources (e.g., competitor websites, review sites like G2/Capterra, SEC filings, patent databases, and social channels), which the agent would read and interpret to drive alerts, battlecards, and next actions—exposing it to untrusted, user-generated content that can influence behavior.