Nano Hub

Warn

Audited by Snyk on Feb 16, 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 ingests untrusted, user-provided images via public URLs (explicitly using catbox.moe for uploads and accepting arbitrary image_urls) and passes those images into subagent prompts and image-generation/editing workflows for interpretation, exposing the agent to third-party content that could carry indirect prompt injection.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Feb 16, 2026, 01:28 AM