deduplication
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: 0.70). The skill is explicitly written to aggregate and deduplicate articles from multiple external sources (see deduplicateArticles and the usage example using fetchFromSourceA/B/C) and references processing news domains and article content from public websites, so it consumes untrusted third-party content as part of its workflow.
Audit Metadata