seo-keywords

Warn

Audited by Snyk on Feb 20, 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's required workflow (SKILL.md) explicitly instructs the agent to fetch and scrape open/public third-party sites and SERPs (e.g., "firecrawl map {competitor-domain}" and "firecrawl scrape {competitor-url}" and "firecrawl search ..." to analyze top 10 Google results), so untrusted web content is ingested and used to drive clustering, difficulty scoring, and next actions.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Feb 20, 2026, 05:32 PM