The Agent Skills Directory

[PROMPT_INJECTION]: The skill contains standard instructional language focused on development workflows. No attempts to override agent behavior, bypass safety guidelines, or extract system prompts were detected.- [DATA_EXFILTRATION]: No sensitive file paths (e.g., SSH keys, AWS credentials) are accessed. References to local files are restricted to project-specific source code and documentation. No unauthorized network operations were found.- [REMOTE_CODE_EXECUTION]: There are no commands or patterns that download and execute remote scripts. Links to external sites are limited to official documentation for the relevant software libraries.- [EXTERNAL_DOWNLOADS]: The skill references shared styleguides hosted on the author's (cofin) GitHub repository. These are static documentation files and do not involve executable code or unverifiable dependencies.- [COMMAND_EXECUTION]: No dangerous system commands or privilege escalation patterns (like sudo or chmod) are present in the skill instructions.- [SAFE]: The skill is a standard development guide that follows best practices for providing context to an AI agent without introducing security vulnerabilities.

sqlspec-aiosqlite