card

Warn

Audited by Snyk on Apr 19, 2026

Risk Level: MEDIUM
Full Analysis

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

  • Third-party content exposure detected (high risk: 0.90). The skill explicitly accepts URLs and in "获取内容" states "URL:优先用轻量网页读取方式抓正文", so it fetches and ingests open/public web pages as required input and uses that untrusted/user-generated content to drive mode selection and HTML/PNG generation, which could allow indirect prompt-injection from third-party pages.

Issues (1)

W011
MEDIUM

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

Audit Metadata
Risk Level
MEDIUM
Analyzed
Apr 19, 2026, 02:49 PM
Issues
1