Noma Security reports that instructions submitted through a public Web-to-Lead form could later steer Agentforce to send CRM data to a domain on Salesforce's allowlist that had expired and could be re-registered. Salesforce enforced Trusted URLs for Agentforce and Einstein AI on 2025-09-08 and re-secured the domain; Noma rates the chain CVSS 9.4.
Why it matters
Stale allowlist entries turned a trusted exfiltration path into an attacker-controlled one.
Key facts
As stated in the sources, with where to find them.
- Reported 2025-07-28; acknowledged 2025-07-31; Trusted URLs enforcement 2025-09-08; disclosed 2025-09-25.Timeline
Findings that cite this record
Key questions this bears on
- Can prompt injection against AI agents be reliably defended?Not reliably. Bounding what untrusted input can trigger helps, but trust boundaries must survive delegation and tool execution.
- Where are deployed AI agents actually being exploited?Exploitation often reaches deployed agents through connectors, credentials, tools and packages.
Sources
Related records
Oct 31, 2025
Oct 8, 2025
Aug 20, 2025
Aug 6, 2025
Aug 20, 2024
Feb 13, 2026