agent-browser

HIGH W007: Insecure credential handling detected in skill instructions.

• Insecure credential handling detected (high risk: 1.00). The prompt includes examples that embed secrets verbatim in CLI commands and interactions (e.g., fill "password123", proxy URLs with user:pass, set credentials user pass, cookies set name value), which would require the agent to handle and output secret values directly.

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

• Third-party content exposure detected (high risk: 0.90). This skill explicitly navigates to arbitrary URLs ("agent-browser open ") and snapshots/reads page content ("agent-browser snapshot -i", "agent-browser get text/html @e1") as part of its core workflow in SKILL.md, meaning it ingests untrusted public web content that can influence subsequent actions (clicks, fills, navigation).