devonthink

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

• Third-party content exposure detected (high risk: 0.90). The skill's SKILL.md and references/jxa-api.md explicitly include Web Import and download functions (e.g., createMarkdownFrom/createPDFDocumentFrom/downloadMarkupFrom/downloadJSONFrom) that fetch arbitrary URLs and the skill also reads and summarizes record content via AI features, so it clearly ingests untrusted third‑party web content that can influence agent actions.