servicenow
Pass
Audited by Gen Agent Trust Hub on Mar 1, 2026
Risk Level: SAFEPROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [COMMAND_EXECUTION]: The skill executes
curlandjqcommands to interact with the ServiceNow Table API. These are standard system utilities used as intended for the skill's primary management functions. - [PROMPT_INJECTION]: The skill retrieves and processes external data from ServiceNow incidents and change requests, creating a potential surface for indirect prompt injection through ticket fields like
short_descriptionanddescription. - Ingestion points:
curlresponses containing ticket metadata and descriptions fetched inSKILL.md. - Boundary markers: None identified in the shell command templates.
- Capability inventory: Network read/write access via
curlto ServiceNow endpoints. - Sanitization: No explicit sanitization or filtering of the retrieved ticket content is performed before presentation to the agent.
Audit Metadata