peer-review

Warn

Audited by Snyk on Apr 16, 2026

Risk Level: MEDIUM
Full Analysis

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

  • Potentially malicious external URL detected (high risk: 0.90). The skill's runtime scripts make authenticated API calls to the OpenRouter endpoint (https://openrouter.ai/api/v1 and guidance link https://openrouter.ai/keys) to generate images and receive text critiques that are directly injected into and used to modify subsequent prompts (iterative prompt refinement), and the tool requires an OPENROUTER_API_KEY to run, so this external URL is a required runtime dependency that controls agent prompts.

Issues (1)

W012
MEDIUM

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

Audit Metadata
Risk Level
MEDIUM
Analyzed
Apr 16, 2026, 10:49 PM
Issues
1