Skip to content
Fencer Intel
medium 5.3

CVE-2025-64321 json

Improper Neutralization of Input Used for LLM Prompting vulnerability in Salesforce Agentforce Vibes Extension allows Manipulating Writeabl…

published last yr. modified 4mo ago also EUVD-2025-37829

cvss
5.3
version 3.1, CNA
cisa kev
Not listed
not in CISA's catalog
epss
0.2%
EPSS 0.2% chance of exploitation in 30 days, percentile 14%
public exploits
0
none known

Summary

Improper Neutralization of Input Used for LLM Prompting vulnerability in Salesforce Agentforce Vibes Extension allows Manipulating Writeable Configuration Files.This issue affects Agentforce Vibes Extension: before 3.3.0.

Patch / fix

  • Salesforce Agentforce Vibes Extension 3.3.0

Is CVE-2025-64321 in your stack? Fencer shows which of your repositories are affected as soon as an advisory lands, and opens the fix as a pull request.

Check with Fencer

CISA SSVC

Exploitation
none
Automatable
yes
Technical impact
partial
Assessed
last yr.

Exploit prediction

0.24% chance of exploitation in the next 30 days, higher than 14% of all scored CVEs (FIRST EPSS, 2026-11-09).

CVSS scores

assigned by version score vector
CISA ADP 3.1 5.3 CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:N/I:L/A:N
CNA 3.1 5.3 CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:N/I:L/A:N

Affected products

  • Salesforce Agentforce Vibes Extension

Classification

Weakness
  • CWE-1427 Improper Neutralization of Input Used for LLM Prompting
  • CWE-94 Improper Control of Generation of Code

References

Sources

Fencer Intel keeps one entry per vulnerability: the CVE id wins, then GHSA, and records that alias each other are merged, except that two CVEs always keep separate entries. The same data is available as JSON.