seo-audit
Warn
Audited by Snyk on Mar 5, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (high risk: 0.90). The skill explicitly fetches and crawls live, arbitrary websites (HTML, rendered DOM via Playwright, robots.txt, sitemap) as shown in SKILL.md and docs/ai-agent-integration.md, and agents are instructed to parse those untrusted pages and then prioritize or even "fix" issues—so third-party content can materially influence agent decisions and actions.
Audit Metadata