agent-browser

HIGH W007: Insecure credential handling detected in skill instructions.

• Insecure credential handling detected (high risk: 1.00). The prompt includes explicit plaintext credentials in command examples (e.g., fill "password123") and workflows that save/load authentication state files, which require the agent to handle and potentially emit secret values verbatim.

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

• Third-party content exposure detected (high risk: 0.95). The required runtime workflow uses agent-browser open <url> and agent-browser snapshot to fetch and parse arbitrary web page content (outsider-authored public web text) into the agent’s context via the snapshot output/element text.