querying-soql
Pass
Audited by Gen Agent Trust Hub on May 14, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: All components of the skill, including the instructions and the Python validation script, are consistent with the primary purpose of helping users author and optimize Salesforce SOQL queries. The skill promotes industry-standard security practices for Salesforce development.
- [COMMAND_EXECUTION]: The documentation and asset files reference official Salesforce CLI ('sf') commands for executing queries and performance analysis. No automated or hidden shell command execution patterns were found.
- [DATA_EXFILTRATION]: There is no evidence of unauthorized network activity or credential harvesting. The skill includes explicit guidance on using 'WITH SECURITY_ENFORCED' and 'WITH USER_MODE' to prevent unauthorized data access within Salesforce.
- [PROMPT_INJECTION]: The skill's instructions focus on technical guidance for SOQL syntax and governor limits. No patterns attempting to bypass agent safety filters or override system instructions were detected.
- [EXTERNAL_DOWNLOADS]: The skill does not perform any remote code downloads or script execution from the internet. All logic is contained within the provided scripts or references well-known official developer tools.
Audit Metadata