remote-browser

HIGH W007: Insecure credential handling detected in skill instructions.

• Insecure credential handling detected (high risk: 1.00). The skill exposes commands that accept and return arbitrary plaintext values (e.g., browser-use input "...", cookies get/set, cookies export, and the example chaining showing a raw "password"), which requires the LLM to include secret values verbatim in generated commands/outputs and thus creates an exfiltration risk.

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

• Third-party content exposure detected (high risk: 1.00). This skill explicitly opens arbitrary URLs and extracts/interacts with live web pages (e.g., the "browser-use open " command plus "browser-use state", "browser-use get html", "browser-use get text", and interaction commands in SKILL.md), so it consumes untrusted third‑party web content that can influence subsequent actions.