NYC

article-extractor

Warn

Audited by Snyk on Feb 15, 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 downloads and extracts article content from arbitrary public URLs using reader/trafilatura or a curl-based fallback (e.g., reader "URL", trafilatura --URL "URL", curl "URL"), then reads and previews that untrusted third-party webpage content as part of its workflow, which could enable indirect prompt injection.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Feb 15, 2026, 08:26 PM