NYC

supabase-mcp-integration

Warn

Audited by Snyk on Feb 15, 2026

Risk Level: MEDIUM
Full Analysis

MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).

  • Third-party content exposure detected (high risk: 0.70). The skill includes realtime chat and storage examples (SKILL.md and EXAMPLES.md) that subscribe to database channels like "messages" and display payload.new.content and fetch files via supabase.storage.getPublicUrl/download, meaning it clearly ingests and renders untrusted user-generated content from third-party users.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Feb 15, 2026, 09:07 PM