digital-pr

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

• Third-party content exposure detected (high risk: 0.90). The skill's required workflow explicitly instructs the agent to ingest and act on public third-party content — e.g., "Study recent coverage: Read their last 5-10 articles" and "Check social media: Follow them on Twitter/X" — which the agent is expected to read and use to shape pitches, angles, and outreach decisions, exposing it to untrusted/user-generated web content that can influence actions.