camoufox

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

• Third-party content exposure detected (high risk: 1.00). The skill's runtime scripts explicitly navigate to arbitrary public URLs and read page content (e.g., scripts/browse.py and scripts/login_session.py call page.goto(args.url) and page.inner_text('body')), so it ingests untrusted third-party web content that the agent is expected to interpret as part of its workflow.