claude-design-hyperframes

Warn

Audited by Snyk on Apr 23, 2026

Risk Level: MEDIUM
Full Analysis

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

  • Third-party content exposure detected (high risk: 1.00). The SKILL.md Step 1 "Inputs" explicitly requires the agent to perform web_search / web_fetch on public sites (company blogs, Wikipedia, TechCrunch, etc.) and to follow user-provided URLs, so the agent will fetch and interpret untrusted third‑party web content which can materially influence composition decisions.

Issues (1)

W011
MEDIUM

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

Audit Metadata
Risk Level
MEDIUM
Analyzed
Apr 23, 2026, 08:55 PM
Issues
1