page-seo-generator
Warn
Audited by Snyk on Jul 23, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (high risk: 0.85). Yes—Phase 1.5 loads competitor URLs from the (user-provided/outsider) keyword research results and uses Playwright to extract
document.titleand<meta name="description">from OUTSIDER-authored web pages, which are then logged and included in the agent’s subsequent LLM context/output.
MEDIUM W012: Unverifiable external dependency detected (runtime URL that controls agent).
- Potentially malicious external URL detected (high risk: 0.90). The skill runs a Playwright-based fetcher at runtime to load competitor pages and extract Title/meta description (used to shape TDK prompts), as shown by the example competitor URL https://www.canva.com/features/image-upscaler which will be fetched and used to control the agent's outputs.
Issues (2)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
W012
MEDIUMUnverifiable external dependency detected (runtime URL that controls agent).
Audit Metadata