article-extractor

Warn

Audited by Snyk on Mar 1, 2026

Risk Level: MEDIUM
Full Analysis

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

  • Third-party content exposure detected (high risk: 0.90). This skill explicitly downloads and extracts arbitrary public web articles from user-provided URLs (see Extraction Methods / Complete Workflow using reader "URL", trafilatura --URL "URL", or curl -s "URL"), ingesting untrusted third-party article text and titles into the agent's workflow (saving, previews, and optional follow-up actions), which could enable indirect prompt injection.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Mar 1, 2026, 01:08 AM