code-search

Warn

Audited by Snyk on Mar 9, 2026

Risk Level: MEDIUM
Full Analysis

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

  • Third-party content exposure detected (high risk: 0.80). This skill uses the comfy-codesearch service to search "ComfyUI core and custom nodes registry" and returns code snippets and GitHub URLs (public/user-generated repositories) that the agent will read and could contain untrusted, user-generated content capable of influencing subsequent actions.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Mar 9, 2026, 06:35 PM