image-analysis

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

• Third-party content exposure detected (high risk: 0.90). The skill accepts an image_url (SKILL.md and tools.ts) and handler.ts passes imageUrl into VisionService.analyzeImage (which fetches and analyzes the remote image), so the agent will fetch and interpret arbitrary, untrusted web-hosted images whose content (including embedded text/instructions) can influence analysis and subsequent agent decisions.