marketing-seo
Warn
Audited by Snyk on Aug 3, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (medium risk: 0.30). The SEO skill’s required workflow uses
agent-browserto open and then ingest free-text from multiple arbitrary third-party web pages at runtime (e.g., Google SERPs, SimilarWeb pages, PageSpeed reports, Schema validator pages, and AnswerThePublic results) viaagent-browser get text body.
MEDIUM W012: Unverifiable external dependency detected (runtime URL that controls agent).
- Potentially malicious external URL detected (high risk: 1.00). The skill's agent-browser setup instructs installing remote code at runtime using "npx skills add https://github.com/vercel-labs/agent-browser --skill agent-browser", which fetches and executes code and is required for the live research workflow.
Issues (2)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
W012
MEDIUMUnverifiable external dependency detected (runtime URL that controls agent).
Audit Metadata