help

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

• Third-party content exposure detected (high risk: 1.00). The skill's SKILL.md explicitly shows commands that accept and audit arbitrary public URLs (e.g., "/dm:seo-audit https://example.com" in the Example Prompts section), indicating the agent will fetch and interpret untrusted third-party web content to produce action items and thus could be influenced by indirect prompt injection.