AI Image Generator & Editor — GPT Image 2, Nanobanana, ComfyUI

Warn

Audited by Snyk on Apr 30, 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 explicitly accepts and fetches user-supplied image URLs as referenceImages (see "Mode 5: Edit/Modify Existing Image" and "Mode 7: Reference Image Generation" which allow passing image URLs or gallery URLs), meaning it ingests untrusted public third‑party content that the agent reads and uses to drive generation decisions.

MEDIUM W012: Unverifiable external dependency detected (runtime URL that controls agent).

  • Potentially malicious external URL detected (high risk: 0.80). The Quick Start requires running "npx meigen@1.2.13", which fetches and executes remote code from the npm package (https://www.npmjs.com/package/meigen) at runtime and is a required dependency that controls the MCP server's behavior.

Issues (2)

W011
MEDIUM

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

W012
MEDIUM

Unverifiable external dependency detected (runtime URL that controls agent).

Audit Metadata
Risk Level
MEDIUM
Analyzed
Apr 30, 2026, 05:32 PM
Issues
2
Security Audit — snyk — AI Image Generator & Editor — GPT Image 2, Nanobanana, ComfyUI