30x-seo-internal-links
Warn
Audited by Snyk on Mar 9, 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 the agent to crawl and read arbitrary website URLs ("Step 1: Crawl Site", "Input: Website URL", and Generation Mode: "read site existing pages" / "website URL to crawl"), so it ingests untrusted public web content which directly determines link-suggestion decisions and subsequent actions.
Audit Metadata