design-email
Warn
Audited by Snyk on Jul 24, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (high risk: 0.75). The workflow includes runtime calls like
CallMcpToolwithsources: [{ "type": "web" }](web search/firecrawl), which can fetch outsider-authored web page text and feed it into the agent’s LLM context for “Research best practices” and “Deliverability checks.”
MEDIUM W012: Unverifiable external dependency detected (runtime URL that controls agent).
- Potentially malicious external URL detected (high risk: 0.90). The skill includes a runtime import from Deno that will fetch and execute remote code (https://deno.land/std/http/server.ts) in the Supabase Edge Function example, making it a required runtime dependency for that path.
Issues (2)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
W012
MEDIUMUnverifiable external dependency detected (runtime URL that controls agent).
Audit Metadata