agent-browser-harness

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

• Third-party content exposure detected (high risk: 0.90). The skill's workflow and references (notably references/tiktok.md) explicitly open and inspect a public TikTok URL and instruct the agent to read and act on page content (e.g., read caption text, check toggles, verify button labels), which is untrusted, user-generated third‑party content that can influence subsequent tool actions.