The Agent Skills Directory

[SAFE]: The skill provides legitimate utility for Salesforce developers and follows established industry best practices for query optimization and security.
[REMOTE_CODE_EXECUTION]: The skill utilizes platform-specific lifecycle hooks in .claude/hooks.yaml to execute local validation logic.
Evidence: The hook executes python3 ${SKILL_HOOKS}/post-tool-validate.py upon file modifications.
Analysis: The script is provided within the skill package, performs transparent static analysis on SOQL syntax, and does not contain malicious logic, network operations, or unsafe system commands.
[SAFE]: The skill processes natural language to generate SOQL code, which is a standard functional requirement for this use case. It mitigates potential risks by providing detailed documentation and recommending security enforcement patterns such as WITH SECURITY_ENFORCED and WITH USER_MODE.

sf-soql