agent-browser

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

• Third-party content exposure detected (high risk: 0.90). The skill explicitly navigates to arbitrary URLs and ingests page content (e.g., SKILL.md's core workflow "agent-browser open " plus "agent-browser snapshot -i" / "agent-browser get text" and templates/capture-workflow.sh which open a target URL and save page text), so untrusted public webpages can be read and used to drive subsequent actions.