agent-browser-core

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

• Third-party content exposure detected (high risk: 1.00). The skill explicitly requires providing target URLs and its workflows (SKILL.md and references/agent-browser-workflows.md) use commands like "open ", "snapshot", "get html"/"get text" and act via refs, meaning it fetches and interprets arbitrary public web pages (untrusted third-party content) which can materially influence subsequent agent actions.