webcmd-browser

HIGH W007: Insecure credential handling detected in skill instructions.

• Insecure credential handling detected (high risk: 1.00). The skill's examples and commands (e.g., browser type <target> <text> with a password like "hunter2" and eval/get value that can read sensitive fields) require embedding or echoing secret values verbatim into CLI invocations or outputs, creating an exfiltration risk.

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

• Third-party content exposure detected (high risk: 0.85). The skill drives a live browser and can ingest outsider-authored free text from public web pages at runtime via commands like webcmd browser open followed by browser state/get/extract/network (DOM text, extracted Markdown, or API response bodies from arbitrary URLs).