huashu-design

Warn

Audited by Snyk on Apr 28, 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 explicitly requires running WebSearch and fetching/parsing open web resources (e.g., "WebSearch" verification in Core Principle #0 and the Core Asset Protocol steps that crawl brand pages, press kits, App Store/Google Play screenshots, YouTube frame grabs, Wikimedia/Unsplash, etc.) and then uses those fetched facts/assets to populate product-facts.md and brand-spec.md which directly drive design decisions and tool actions, so untrusted third‑party content can materially influence the agent's behavior.

Issues (1)

W011
MEDIUM

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

Audit Metadata
Risk Level
MEDIUM
Analyzed
Apr 28, 2026, 08:47 PM
Issues
1