domain-research
Warn
Audited by Snyk on Feb 17, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (high risk: 0.80). This skill explicitly directs the agent to use open-web MCP servers—notably firecrawl (mcp__firecrawl__firecrawl_scrape) to "scrape: Competitor feature pages" and perplexity for web research—so the agent will ingest and interpret untrusted public web content as part of its workflow.
Audit Metadata