agent-browser

HIGH W007: Insecure credential handling detected in skill instructions.

• Insecure credential handling detected (high risk: 1.00). The skill documentation includes examples that embed plaintext secrets (e.g., "password123" and proxy_username/proxy_password) directly in CLI JSON inputs, forcing an agent to include secret values verbatim in commands/requests.

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

• Third-party content exposure detected (high risk: 0.85). The required runtime workflow navigates to a user-supplied URL and then ingests the page’s extracted text/element descriptions (e.g., elements_text from snapshot/open), which is outsider-authored free text from public web content into the agent’s LLM context.