baoyu-cover-image

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: 1.00). The skill ingests user-supplied reference images and source content (via --ref, pasted images, or article file paths) and explicitly requires deep analysis and inclusion of those external references into the generated prompt (see references/workflow/reference-images.md and references/workflow/prompt-template.md), allowing arbitrary third-party content to dictate mandatory "MUST/REQUIRED" instructions for generation.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Mar 9, 2026, 12:02 PM