AGENTFORCE-22.1: Unsafe Autonomous HTTP Callouts

🚨 Critical · SSRF

Detects Apex classes invoked by agent actions that make HTTP callouts to dynamically-constructed endpoints without Named Credential enforcement. This enables SSRF: a prompt injection attack can redirect the agent's HTTP callout to an attacker-controlled server or internal network resource.

Details

Field	Value
Rule ID	AGENTFORCE-22.1
Severity	Critical
Category	SSRF
Compliance	SOC2_CC7, OWASP_MCP_TOP_10

Remediation

Refer to the SquireX documentation for remediation guidance specific to AGENTFORCE-22.1.

See Also

• Rule catalog index
• SquireX scan documentation