problem-management
Pass
Audited by Gen Agent Trust Hub on Feb 23, 2026
Risk Level: SAFE
Full Analysis
- [COMMAND_EXECUTION]: The skill uses the tool
snow_execute_script_with_outputto perform server-side automation, such as proactive problem identification based on incident patterns. This behavior is consistent with the primary purpose of a ServiceNow development skill. - [PROMPT_INJECTION]: The skill includes search functionality that ingests incident descriptions to query the Known Error Database. While this creates a surface for indirect data processing, it is used for legitimate search operations within the ServiceNow environment and does not attempt to bypass agent safety filters.
- [DATA_EXFILTRATION]: The skill interacts with ServiceNow tables such as
problem,incident, andknown_error. These operations are conducted using standard GlideRecord APIs for the purpose of record management and do not involve unauthorized data transfer to external domains.
Audit Metadata