supadata

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

• Third-party content exposure detected (high risk: 1.00). The SKILL.md explicitly instructs the agent to fetch and scrape public, user-generated content (e.g., "Get YouTube Video Transcript" via /v1/transcript and "Scrape Web Page to Markdown" via /v1/web/scrape), which the agent will read and use for AI processing, exposing it to untrusted third-party content that could carry indirect prompt injections.