analytics-insights
Warn
Audited by Snyk on Feb 28, 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's SKILL.md explicitly instructs scraping and analyzing public, user-generated X pages (e.g., x.com/USERNAME, x.com/search?q=%23tag, x.com/USERNAME/followers) and uses that scraped content to generate recommendations and drive actions (scheduling, audits, A/B tests), so untrusted third-party content can directly influence agent decisions.
Audit Metadata