agent-browser-assistant

HIGH W007: Insecure credential handling detected in skill instructions.

• Insecure credential handling detected (high risk: 0.90). The skill includes plaintext password values in example form-fill calls (e.g., "password123"), which instructs the agent to insert secret values verbatim into generated browser actions/outputs, creating an exfiltration risk.

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

• Third-party content exposure detected (medium risk: 0.30). The required runtime workflow for the browser tool explicitly supports opening arbitrary URLs and extracting page content/snapshots, meaning outsider-authored free text from websites the user navigates to can be ingested.