agent-browser

HIGH W007: Insecure credential handling detected in skill instructions.

• Insecure credential handling detected (high risk: 1.00). The prompt's examples and CLI usage explicitly embed plaintext credentials (e.g., agent-browser fill @e2 "password123") and show saving/loading auth state, which requires the agent to handle and output secret values verbatim and therefore poses an 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 navigate to arbitrary URLs and run commands like "agent-browser open " and "agent-browser snapshot -i" which fetch and parse public web pages (untrusted, user-provided content) that the agent is expected to read and act on, so third-party page content could influence subsequent actions.