news-tracker

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: 0.90). The skill performs multiple search_web calls and incorporates titles, URLs, summaries and source content from public third-party sites (e.g., TechCrunch, Reuters, Hacker News and arbitrary search result URLs returned by search_web) into its news lists and Q&A, so the agent ingests untrusted web content that could enable indirect prompt injection.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Feb 16, 2026, 02:54 AM