credential-setup-with-computer-use

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

• Third-party content exposure detected (high risk: 0.75). SKILL.md instructs using research(action="fetch-url") / research(action="web-search") to read external n8n credential docs and then using browser_content/browser_snapshot to ingest provider page text at runtime, which can include outsider-authored free text (public web content) into the LLM context.