article-extractor

Warn

Audited by Snyk on Feb 16, 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). This skill fetches and processes arbitrary public web pages (e.g., extract_jina calling https://r.jina.ai/$url, the curl-based fallback that downloads the provided URL, and Wayback Machine queries to archive.org), so it ingests untrusted third-party/user-generated content that the agent reads and interprets.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Feb 16, 2026, 01:59 AM