supabase-rls-policy-generator

Pass

Audited by Gen Agent Trust Hub on Feb 17, 2026

Risk Level: SAFE
Full Analysis
  • [Indirect Prompt Injection] (LOW): The skill ingests external data from user-provided schema files to analyze database structures. This represents a potential surface for indirect instructions to be processed by the agent.
  • Ingestion points: SKILL.md Step 1 (database schema file path or table names).
  • Boundary markers: Absent; no delimiters are defined for separating schema content from agent instructions.
  • Capability inventory: The skill is limited to text generation (SQL migration files, documentation, and test queries). It does not include tools for file system writing, network requests, or shell execution.
  • Sanitization: Absent; the skill processes schema data directly to generate policy names and conditions.
  • [Privilege Escalation] (SAFE): While the skill generates SQL code involving high-privilege operations (e.g., ALTER TABLE, CREATE POLICY, SECURITY DEFINER functions), these are standard for database administration tasks. The skill does not execute these commands itself; it only provides them as output for the user's migration scripts.
Audit Metadata
Risk Level
SAFE
Analyzed
Feb 17, 2026, 06:26 PM