image-gen

Warn

Audited by Snyk on Mar 13, 2026

Risk Level: MEDIUM
Full Analysis

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

  • Third-party content exposure detected (high risk: 0.70). The skill's Step 4 "Reference Images" (and references/prompt-guide.md) explicitly asks for and ingests user-provided public image URLs (e.g., imgur, imgbb), which are untrusted third‑party content that the agent uses to influence image generation, so external content can materially affect behavior.

Issues (1)

W011
MEDIUM

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

Audit Metadata
Risk Level
MEDIUM
Analyzed
Mar 13, 2026, 05:03 AM
Issues
1