client-scripts

Pass

Audited by Gen Agent Trust Hub on Sep 6, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill provides templates for ServiceNow client scripts that ingest untrusted user input from form fields using g_form.getValue() and onChange parameters. This data is subsequently processed or transmitted to server-side components.\n
  • Ingestion points: Untrusted data enters the context via g_form.getValue() and the newValue parameter in onChange functions within SKILL.md.\n
  • Boundary markers: The provided templates do not include specific delimiters or instructions to ignore embedded commands within user-supplied values.\n
  • Capability inventory: The skill uses tools like snow_create_client_script and snow_create_script_include to implement the logic that processes this data.\n
  • Sanitization: While a basic email regex validation is provided in the onSubmit pattern, comprehensive sanitization or output encoding is not detailed in the generic templates.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 6, 2026, 07:16 PM
Security Audit — agent-trust-hub — client-scripts