request-management
Pass
Audited by Gen Agent Trust Hub on Feb 23, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill utilizes the
snow_execute_script_with_outputtool to run server-side JavaScript on the ServiceNow platform, which is a high-privilege administrative capability. - [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection because it reads data from potentially untrusted ServiceNow tables (via
snow_query_table) and provides tools for script execution. The instructions do not include boundary markers or sanitization to mitigate instructions embedded in those records. - [SAFE]: No obfuscation, hardcoded credentials, or unauthorized network activity was identified in the code or metadata.
Audit Metadata