BaseFortify

Publication date: 2025-11-04

Last updated on: 2026-02-04

Assigner: Salesforce, Inc.

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 Scores

EPSS Scores

Probability:
Percentile:

Meta Information

Published

2025-11-04

Last Modified

2026-02-04

Generated

2026-07-06

AI Q&A

2025-11-04

EPSS Evaluated

2026-07-05

NVD

CVE-2025-64320

Affected Vendors & Products

Vendor	Product	Version / Range
salesforce	agentforce_vibes_extension	*

Helpful Resources

Exploitability

CWE

KEV

CWE ID	Description
CWE-94	The product constructs all or part of a code segment using externally-influenced input from an upstream component, but it does not neutralize or incorrectly neutralizes special elements that could modify the syntax or behavior of the intended code segment.

Attack-Flow Graph

Executive Summary

This vulnerability is an Improper Neutralization of Input Used for LLM Prompting in the Salesforce Agentforce Vibes Extension, which allows an attacker to perform code injection. It affects versions of the Agentforce Vibes Extension before 3.2.0.

Impact Analysis

The vulnerability can allow an attacker to inject malicious code through improperly neutralized input used for LLM prompting, potentially leading to unauthorized actions or compromise within the affected Salesforce extension.

Hi! I’m here to help you understand CVE-2025-64320. Ask me anything about the vulnerability, its impact, or mitigation strategies.

0/70