AGENTFORCE-2.3: Prompt Injection Defense Heuristics

🔴 High · Agent Script Safety

Detects when dynamic user input variables are injected into prompt templates or agent instructions without defensive boundary patterns, creating vulnerability to prompt injection attacks that can override system instructions and bypass security policies.

Details

Field	Value
Rule ID	AGENTFORCE-2.3
Severity	High
Category	Agent Script Safety
Compliance	EU_AI_ACT_HIGH_RISK, NIST_AI_RMF

Remediation

Refer to the SquireX documentation for remediation guidance specific to AGENTFORCE-2.3.

See Also

• Rule catalog index
• SquireX scan documentation