agent-browser

HIGH W007: Insecure credential handling detected in skill instructions.

• Insecure credential handling detected (high risk: 1.00). The skill's examples and commands show filling form fields with literal credentials (e.g., fill @e4 "password123") and instruct the agent to perform logins, which would require embedding and outputting 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: 1.00). The skill's required workflow (SKILL.md and references/ai-snapshot-workflow.md) instructs the agent to open arbitrary URLs with "agent-browser open " and run "agent-browser snapshot" / "get text/get html", causing the agent to fetch and interpret untrusted public web pages which can directly influence subsequent actions (clicks, fills, navigation).