servicenow
Pass
Audited by Gen Agent Trust Hub on Jun 14, 2026
Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill uses
curlandjqwithin several documented examples to perform operations like fetching incidents, updating records, and parsing JSON responses. - [EXTERNAL_DOWNLOADS]: The skill makes network requests to
*.service-now.comto interact with ServiceNow's REST API. ServiceNow is a well-known enterprise service provider. - [PROMPT_INJECTION]: The skill exhibits a surface for indirect prompt injection (Category 8).
- Ingestion points: Data is ingested from external ServiceNow tables including
incident,change_request,sys_user, andcmdb_civiacurlcommands. - Boundary markers: No explicit boundary markers or instructions to ignore embedded commands are present in the provided command examples.
- Capability inventory: The skill utilizes
curlfor network and file operations (e.g.,-d @/tmp/servicenow_request.json) andjqfor data processing. - Sanitization: No explicit sanitization or filtering of the content retrieved from ServiceNow is demonstrated before it is presumably processed by the agent.
Audit Metadata