flow-generation
Warn
Audited by Gen Agent Trust Hub on Sep 15, 2026
Risk Level: MEDIUMINDIRECT_PROMPT_INJECTIONDYNAMIC_EXECUTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted natural language descriptions from users to generate ServiceNow flows, creating a risk that malicious instructions could influence system modifications.
- Ingestion points: Natural language input describing flow requirements (parsed in Step 1).
- Boundary markers: No explicit delimiters or instructions to ignore embedded malicious commands are present.
- Capability inventory: The skill utilizes SN-Create-Record and SN-Update-Record tools to modify the ServiceNow instance and supports generating scripted flow steps.
- Sanitization: There is no documented validation or sanitization of user input before it is used to create or update records.
- [DYNAMIC_EXECUTION]: The skill facilitates the generation of ServiceNow JavaScript code to be stored and executed within the platform.
- Evidence: Step 5 details adding 'Run Script' actions using the sn_fd.run_script action type. The agent is expected to generate the script content based on user descriptions.
- Impact: This results in the automated creation of executable code within the target environment based on potentially unverified user input.
Audit Metadata