huashu-design-html-native

Warn

Audited by Snyk on Apr 21, 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.md's mandatory "Brand Asset Protocol" explicitly instructs the agent to search and download live pages/assets from public brand sites (e.g., ".com/brand", ".com/press") and to ingest the downloaded HTML/SVG to extract colors and generate the design, which clearly fetches and interprets untrusted third‑party web content as part of its workflow.

Issues (1)

W011
MEDIUM

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

Audit Metadata
Risk Level
MEDIUM
Analyzed
Apr 21, 2026, 07:41 AM
Issues
1