CVE-2025-64320mediumCWE-1427

CVE-2025-64320: medium-severity vulnerability in Salesforce Agentforce Vibes Extension

Published · Updated

E-mail alert when it lands in KEV, gets a public PoC or its score goes up.

13Vexday Risk Score

No sign of exploitation. No public exploitation artifact known so far.

ssvc Trackcvss 6.5epss 0.2%
In short

The Salesforce Agentforce Vibes Extension fails to properly filter user input before sending it to an AI language model, allowing attackers to inject malicious code or commands that the AI may execute.

Technical detail

CWE-1427 describes improper neutralization of LLM prompt inputs; an unauthenticated or low-privilege attacker can supply crafted input that bypasses validation, leading to prompt injection and potential code execution through the AI model in Agentforce Vibes Extension versions before 3.2.0.

Summary generated and translated by AI from the official description.
Improper Neutralization of Input Used for LLM Prompting vulnerability in Salesforce Agentforce Vibes Extension allows Code Injection.This issue affects Agentforce Vibes Extension: before 3.2.0.
CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:L/I:L/A:N
Related CVEs — Salesforce Agentforce Vibes Extension

In the same product, most dangerous first.