presto-design

Warn

Audited by Snyk on Apr 11, 2026

Risk Level: MEDIUM
Full Analysis

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

  • Third-party content exposure detected (high risk: 0.80). The skill explicitly accepts a user-provided brand URL or image and instructs the agent to "Extract: dominant colors, typography, spacing…" (context/design-spec.md Path B) and SKILL.md §1 routes to that workflow when no DESIGN.md exists, which means the agent will fetch/interpret external public site assets that can directly drive DESIGN.md (the authoritative spec) and thus materially influence subsequent actions — creating a clear avenue for indirect prompt injection.

Issues (1)

W011
MEDIUM

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

Audit Metadata
Risk Level
MEDIUM
Analyzed
Apr 11, 2026, 10:44 AM
Issues
1
Security Audit — snyk — presto-design