background-jobs

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

• Third-party content exposure detected (high risk: 0.90). The skill enqueues and processes user-provided URLs for analysis (examples/arq-fastapi.md shows create_analysis calling service.create(request.url) and app/tasks/analysis_tasks.py/process_analysis explicitly "fetches content from URL" and calls an LLM), which means it ingests untrusted third-party web content that the agent will read and interpret.