agentkits-marketing-automation

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

• Third-party content exposure detected (high risk: 0.90). The SKILL.md explicitly shows commands that take and analyze public URLs (e.g., /competitor:deep "asana.com", /seo:audit "website-url.com", /seo:programmatic and other workflows that accept arbitrary competitor or website URLs), indicating the agents will fetch and interpret untrusted third‑party web content as part of their workflow.