The Agent Skills Directory

[SAFE]: The skill provides a legitimate security utility for auditing database multi-tenancy. No patterns of prompt injection, malicious persistence, or obfuscation were detected.
[COMMAND_EXECUTION]: The skill utilizes a local script, scripts/parse-schema.mjs, to perform static parsing of DDL snapshots and schema files. This execution is part of the skill's core functionality for security analysis.
[DATA_EXFILTRATION]: The skill performs SQL queries against a PostgreSQL database using the $DATABASE_URL environment variable. These queries are restricted to reading database metadata (such as pg_class for RLS status and pg_index for index structures) and do not involve exfiltrating data to external domains or unauthorized third parties.

db-multitenancy