agent-browser

HIGH W007: Insecure credential handling detected in skill instructions.

• Insecure credential handling detected (high risk: 0.90). The prompt includes commands and examples that pass credentials and passwords as literal CLI arguments (e.g., fill "password123", proxy URLs with user:pass, set credentials user pass, cookies/storage set name value), which encourages embedding secrets verbatim in outputs.

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

• Third-party content exposure detected (high risk: 0.90). The skill explicitly navigates and ingests arbitrary public web content (e.g., "agent-browser open " in SKILL.md and the capture template templates/capture-workflow.sh which runs agent-browser snapshot -i and agent-browser get text body), and includes scraping/rotating-proxy examples (references/proxy-support.md) so the agent will read and interpret untrusted third‑party/user-generated pages.