context-engine
Warn
Audited by Snyk on Mar 5, 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 instructs scraping and monitoring of open/public third-party sources (e.g., "scrape pricing pages", "check competitor blog RSS feeds or scrape blog index pages", HTML diffing and screenshot captures, Google Ads Transparency Center, Meta Ad Library, social media and news APIs) in competitive-monitoring-guide.md and related workflow docs, so the agent will fetch and interpret untrusted web/social content that can drive alerts and automated decisions.
Audit Metadata