object-removal

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 explicitly accepts arbitrary image_urls in its Quick Start and examples (which the service fetches and ingests) and the SSE events docs include web_search_query/web_search_citations, showing the agent performs web searches and consumes external URLs—untrusted third‑party content that can influence decisions and tool use.