robotframework-selenium-skill

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

• Third-party content exposure detected (high risk: 0.90). The skill instructs the agent to open and navigate arbitrary URLs and web pages (e.g., Open Browser ${URL}, Go To ${URL}, Open URLs In Tabs/window.open) and to read/inspect their content (Get Source, Get Text, Execute JavaScript, read iframe src), which clearly ingests untrusted/public third‑party page content that could carry indirect prompt injections.