use-my-browser

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

• Third-party content exposure detected (high risk: 0.90). The skill's SKILL.md, README examples, and references (e.g., references/browser-recipes.md and references/tool-matrix.md) explicitly instruct the agent to use public-web tools (web.search_query, web.open, raw fetch) and chrome-devtools to read and extract content from public websites and social platforms (e.g., "Go to X.com", "Pull the real image or video source"), so the agent will ingest untrusted third-party, user-generated content that can influence subsequent actions.