seo-expert
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: 0.80). The skill explicitly instructs using public search data and sites—e.g., "Google Autocomplete", "People Also Ask", "Related searches", "Ahrefs/SEMrush suggestions" and tasks like "find broken links on relevant sites"—which require fetching and interpreting content from arbitrary public websites, exposing the agent to untrusted third-party content.
Audit Metadata