SNOW-9.1: Prompt Injection Vector in Agent Instructions

🚨 Critical · ServiceNow Instruction Integrity

Detects prompt injection vectors in sn_aia_agent instructions, NASK skill markdown, and inbound email action scripts. Inbound email actions are a classic injection path where attacker-controlled content enters the agent's context.

Details

Field	Value
Rule ID	SNOW-9.1
Severity	Critical
Category	ServiceNow Instruction Integrity
Platforms	servicenow

Remediation

Refer to the SquireX documentation for remediation guidance specific to SNOW-9.1.

See Also

• Rule catalog index
• SquireX scan documentation