browser

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

• Third-party content exposure detected (high risk: 0.90). The skill explicitly fetches and processes arbitrary public web pages via commands like browse open <url> and browse snapshot (SKILL.md) and EXAMPLES.md demonstrates browse get text/form interactions that require the agent to read and act on untrusted third-party page content, which could supply instructions affecting subsequent tool use.