browser-qa

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

• Third-party content exposure detected (high risk: 1.00). The skill's required workflow ("Navigate to target URL" and "Uses the browser automation ... to interact with live pages like a real user" in SKILL.md) clearly browses and ingests content from arbitrary live/public web pages and reads/interprets their DOM/console/network as part of its tests, exposing the agent to untrusted third‑party content that could contain indirect prompt-injection.