webpage-to-courseware

Warn

Audited by Snyk on Feb 18, 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 explicitly fetches arbitrary user-provided webpages (via WebFetch and curl) and downloads images (scripts/extract-images.py and scripts/download-images.py) and then parses the HTML and OCRs image contents (Read) as part of its workflow, so it directly ingests untrusted third‑party content that could contain indirect prompt injections.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Feb 18, 2026, 02:25 PM