diagram-design
Warn
Audited by Snyk on Aug 10, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (medium risk: 0.30). In the onboarding flow, the skill reads rendered HTML/CSS/text content from a user-supplied URL (via agent-browser/HTTP fetch) to extract palette+fonts, which means outsider-authored free text can be ingested into the runtime context before the agent rewrites
references/style-guide.md.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata