supabase-rls-policy-generator
Pass
Audited by Gen Agent Trust Hub on Oct 6, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes user-supplied schema files or table definitions to generate SQL code and documentation, creating a potential surface for indirect instructions to influence agent behavior.
- Ingestion points: Step 1 in
SKILL.mddirects the agent to ask for and read database schema file paths or table names provided by the user. - Boundary markers: The instructions lack specific delimiters or instructions to ignore potential natural language commands embedded within the comments or metadata of the ingested schema files.
- Capability inventory: The skill's primary function is text generation (SQL migrations, documentation templates, and testing queries); it does not include instructions for making network requests or performing arbitrary file system writes beyond the documented output files.
- Sanitization: The skill does not provide methods for validating or sanitizing the contents of the ingested schema data before using it to generate output.
Audit Metadata