cmdb-search-analysis
Pass
Audited by Gen Agent Trust Hub on Sep 15, 2026
Risk Level: SAFEDYNAMIC_EXECUTIONINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [DYNAMIC_EXECUTION]: The skill instructions (Step 3 and Step 5) direct the agent to generate and execute ServiceNow background scripts via the
SN-Execute-Background-Scripttool. These scripts are dynamically constructed using string templates to process and aggregate configuration data.\n- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted data from the CMDB, such as CI names and descriptions, which could contain malicious instructions designed to influence the agent's logic.\n - Ingestion points: Data retrieved from ServiceNow tables including
cmdb_ci,cmdb_rel_ci, andservice_ci_assocvia MCP tools or REST endpoints.\n - Boundary markers: No specific boundary markers or delimiters are defined to separate untrusted CI data from system instructions.\n
- Capability inventory: Includes
SN-Execute-Background-Scriptfor server-side code execution, ServiceNow REST API access, and nativeBashcapabilities.\n - Sanitization: The instructions do not specify any sanitization or validation logic for the data ingested from the CMDB before it is processed or presented.\n- [COMMAND_EXECUTION]: The skill utilizes native
Bashcapabilities and ServiceNow REST APIs to perform network-based search operations and metadata retrieval.
Audit Metadata