ideate

Warn

Audited by Snyk on Jul 15, 2026

Risk Level: MEDIUM
Full Analysis

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

  • Third-party content exposure detected (medium risk: 0.65). SKILL.md instructs the agent to “load $user-context” and to “attach provided product URLs, Figma files, screenshots, reference images… to the Image Gen generations,” which at runtime can include outsider-authored free text/content from user-provided URLs/files and then be incorporated into the LLM’s context via the confirmed design brief and image-generation prompt.

Issues (1)

W011
MEDIUM

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

Audit Metadata
Risk Level
MEDIUM
Analyzed
Jul 15, 2026, 02:40 AM
Issues
1
Security Audit — snyk — ideate