core

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

• Third-party content exposure detected (high risk: 0.90). The SKILL.md explicitly references scraping/public content workflows (e.g., "Find → /agent:leads (scraping)" in the ACQUIRE Automation Stack and /agent:content and /agent:social in the ENGAGE stack), which instruct the agent to fetch and interpret untrusted third‑party web/social content that will be used to score/drive automation decisions.