The Agent Skills Directory

[Static Analysis] (SAFE): The provided Python script schema_validator.py performs local file reading and regex-based validation on database schema files. It uses standard libraries and does not include any network operations, shell execution, or unsafe deserialization.
[Tool Permissions] (LOW): The skill requests Read, Write, Edit, Glob, Grep tools. These are appropriate for its stated purpose of analyzing and designing database schemas within a project directory.
[Indirect Prompt Injection] (INFO): The skill processes untrusted user data (project schema files). While this is an inherent attack surface for developer tools, the script only performs read operations and reporting. No automated write actions or code execution are triggered by the contents of the processed data.
[Exfiltration & Network] (SAFE): There are no network-capable commands (curl, wget) or hardcoded URLs pointing to external servers. The skill operates entirely on the local file system.

database-design