pgvector-setup

Warn

Audited by Snyk on Feb 16, 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 ingests and stores arbitrary user-provided documents (see the Supabase Edge Function supabase/functions/process-document/index.ts and templates/embedding-table-schema.sql which save document chunks), and the examples (examples/document-search-pattern.md and vector-search-examples.md) show the agent retrieving those chunks and concatenating them into prompts for LLMs, so untrusted third‑party content is read and used at runtime.

MEDIUM W012: Unverifiable external dependency detected (runtime URL that controls agent).

Audit Metadata
Risk Level
MEDIUM
Analyzed
Feb 16, 2026, 02:10 AM