discovery-patterns
Pass
Audited by Gen Agent Trust Hub on Sep 6, 2026
Risk Level: SAFEDATA_EXFILTRATIONCOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTIONDYNAMIC_EXECUTION
Full Analysis
- [DATA_EXFILTRATION]: The skill provides patterns for querying and modifying the
discovery_credentialstable. While intended for administrative setup, this provides a pathway for interacting with sensitive authentication data within the ServiceNow environment.\n- [COMMAND_EXECUTION]: The skill contains templates for ServiceNow "Probes" that execute arbitrary shell commands on MID Servers using theOperatingSystemCommandAPI (e.g.,cat /opt/myapp/version.txt).\n- [INDIRECT_PROMPT_INJECTION]: The skill demonstrates a pattern where data collected from external network devices via probes is directly processed and stored in the CMDB without sanitization.\n - Ingestion points: The
discovery_sensors_scripttemplate ingestsresult.outputfrom external probes.\n - Boundary markers: None.\n
- Capability inventory: The skill has the ability to write to the database (
ci.update()) and execute scripts (snow_execute_script).\n - Sanitization: No input validation or escaping is present in the provided sensor script example.\n- [DYNAMIC_EXECUTION]: The skill utilizes the
snow_execute_scripttool and provides instructions for creating and executing dynamic scripts on both the ServiceNow instance and MID Servers.
Audit Metadata