agent-browser

HIGH W007: Insecure credential handling detected in skill instructions.

• Insecure credential handling detected (high risk: 1.00). The prompt includes explicit examples that embed plaintext credentials (e.g., filling "password123" into form fields and a --headers '{"Authorization": "Bearer token123"}' example), which instructs the agent to place secret values verbatim into commands/requests, creating exfiltration risk.

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

• Third-party content exposure detected (high risk: 0.90). The SKILL.md explicitly instructs the agent to open arbitrary external URLs (e.g., "agent-browser open ") and to snapshot/get text/find elements from pages ("agent-browser snapshot", "get text", "find text"), meaning the agent fetches and interprets untrusted public web content that can directly influence subsequent clicks, fills, and navigation.