agent-browser

HIGH W007: Insecure credential handling detected in skill instructions.

• Insecure credential handling detected (high risk: 0.80). The prompt includes explicit examples that embed plaintext credentials directly into commands and fill actions (e.g., agent-browser fill @e2 "password123", using "$PASSWORD" in fills, and direct CLI auth examples), and security features are opt-in, so an LLM-driven agent may be required to output secret values verbatim—creating 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 explicitly navigates to arbitrary URLs and ingests page content (e.g., SKILL.md core workflow and commands like "agent-browser open ", "agent-browser snapshot -i", "agent-browser get text body" and the templates/capture-workflow.sh that extract page text), so the agent will read untrusted public web content that can influence its subsequent actions.