Supabase

Connect to Supabase for database operations, vector search, and storage. Use for storing data, running SQL queries, similarity search with pgvector, and managing tables. Triggers on requests involving databases, vector stores, embeddings, or Supabase specifically.

Install only if you intend to let the agent operate with administrator-level Supabase access. Prefer a test project or restricted credentials where possible, review every write/delete/raw-SQL action before it runs, and avoid vector-search queries containing secrets, customer data, or proprietary text unless sending that text to OpenAI is acceptable.

Type: OpenClaw Skill Name: supabase Version: 1.0.0 The OpenClaw AgentSkills skill bundle for Supabase is classified as benign. The skill's purpose is to interact with Supabase, which inherently requires access to sensitive environment variables like `SUPABASE_SERVICE_KEY` (full access) and `OPENAI_API_KEY` for vector search. The `SKILL.md` documentation clearly outlines these requirements and the commands, without any prompt injection attempts against the agent. The `scripts/supabase.sh` script uses `curl` to interact with Supabase and OpenAI, properly escaping all user-provided input (e.g., SQL queries, JSON data) using `jq -Rs .` to prevent shell injection vulnerabilities. All network calls are directed to the specified Supabase URL and the OpenAI API, aligning with the stated functionality without evidence of data exfiltration to unauthorized endpoints or other malicious activities.