CVE-2025-64321VulnerabilityPublished 4 Nov 2025Updated 11 Nov 2025

CVE-2025-64321: Salesforce Agentforce Vibes Extension · Improper Neutralization of Input Used for LLM Prompting

Affects Salesforce Agentforce Vibes ExtensionSource CVE Database V5

Not known to be exploited · CVSS 5.3 Medium : upgrade to 3.3.0 when convenient.

Data as of 25 Oct 2026, 19:02 UTC

CVSS 3.1 base score

5.3Medium

How severe the flaw is on the 0–10 CVSS scale.

EPSS: 0.2% chance of exploitation in 30 days – higher than 14% of CVEsExploit Prediction Scoring System: the likelihood attackers will use this flaw soon.
Patch: Available – fixed in 3.3.0

CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:N/I:L/A:N

Attack Vector: Network
Attack Complexity: Low
Privileges Required: None
User Interaction: None
Scope: Unchanged
Confidentiality: None
Integrity: Low
Availability: None

Bold values are the worst case: easiest to exploit or largest impact.

Attack Vector: Network: The vulnerable component is bound to the network stack and the set of possible attackers extends beyond the other options listed, up to and including the entire Internet. Such a vulnerability is often termed 'remotely exploitable' and can be thought of as an attack being exploitable at the protocol level one or more network hops away (e.g., across one or more routers).
Attack Complexity: Low: Specialized access conditions or extenuating circumstances do not exist. An attacker can expect repeatable success against the vulnerable component.
Privileges Required: None: The attacker is unauthorized prior to attack, and therefore does not require any access to settings or files to carry out an attack.
User Interaction: None: The vulnerable system can be exploited without any interaction from any user.
Scope: Unchanged: An exploited vulnerability can only affect resources managed by the same security authority. In this case, the vulnerable component and the impacted component are either the same, or both are managed by the same security authority.
Confidentiality: None: There is no loss of confidentiality within the impacted component.
Integrity: Low: Modification of data is possible, but the attacker does not have control over the consequence of a modification, or the amount of modification is limited. The data modification does not have a direct, serious impact on the impacted component.
Availability: None: There is no impact to availability within the impacted component.

Definitions: FIRST CVSS v3.1 specification.

Exploitation evidence

Disclosed: evidence found.
CVE published 4 Nov 2025
Detectable: no evidence on record.
No public nuclei template indexed
Weaponised: no evidence on record.
No public exploit code indexed in Metasploit or Exploit-DB
Exploited in the wildExploited: no evidence on record.
Not in CISA KEV and no source reports exploitation
Observed by OffSeq MirageSeen by Mirage: no evidence on record.
No attack traffic recorded by OffSeq Mirage sensors

A missing step is not evidence of safety. Sources: cve.org (opens in a new tab), the Metasploit, Exploit-DB and nuclei-templates index as of 2026-10-25.

Disclosed: The CVE record is public on cve.org. Its publication is t = 0.
Detectable: A public nuclei template can find exposed instances, for defenders and attackers alike.
Weaponised: Public exploit code exists in Metasploit or Exploit-DB, or CISA SSVC reports a public proof of concept.
Exploited in the wild: CISA KEV lists it, CISA SSVC rates exploitation active, or a source reports attacks.
Observed by OffSeq Mirage: OffSeq Mirage honeypot sensors recorded attack traffic for this CVE, or found exposed hosts without attack traffic.

Moments are spaced evenly, not to scale; a dashed line marks a gap of six months or more. Deltas count from t = 0. Sources that give only a date (CISA KEV, Exploit-DB, or a time of exactly 00:00Z) read “same day” rather than hours. Metasploit modules carry the flaw’s disclosure date, not their release date, and nuclei templates carry no date, so both appear above but not on the timeline.

What to do

Upgrade Salesforce Agentforce Vibes Extension to 3.3.0.

Affected software

Product	Affected	Fixed in
Salesforce Agentforce Vibes Extension	Affected =0 <3.3.0	Fixed in 3.3.0

AI-suggested

1. Upgrade the Salesforce Agentforce Vibes Extension to version 3.3.0 or later as soon as the patch is released by Salesforce. 2. Until patching is possible, restrict write permissions on configuration files associated with the extension to only trusted administrators and processes. 3. Implement strict input validation and sanitization controls on any user or external inputs that interact with LLM prompting mechanisms within the extension. 4. Monitor configuration files for unauthorized changes using file integrity monitoring tools and alert on suspicious modifications. 5. Employ network-level protections such as web application firewalls (WAFs) to detect and block anomalous requests targeting the extension. 6. Conduct regular security assessments and code reviews focusing on input handling related to LLM integrations. 7. Educate administrators and developers about the risks of improper input neutralization in AI/LLM contexts to prevent similar vulnerabilities. 8. Maintain up-to-date incident response plans to quickly address any exploitation attempts.

Description

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.

Impact

For European organizations, the impact primarily concerns the integrity of customer service and CRM workflows managed through the Salesforce Agentforce Vibes Extension. Manipulation of configuration files could lead to altered system behavior, potentially causing incorrect data processing, misrouting of customer interactions, or enabling secondary attacks through configuration abuse. While confidentiality and availability are not directly affected, the integrity compromise can undermine trust in service operations and lead to compliance issues, especially under GDPR where data processing accuracy is critical. Organizations heavily reliant on Salesforce for customer engagement, particularly in sectors like finance, healthcare, and telecommunications, may face operational disruptions or reputational damage if exploited. The remote, no-authentication nature of the vulnerability increases the risk of automated exploitation attempts, necessitating prompt mitigation. The absence of known exploits in the wild provides a window for proactive defense but should not lead to complacency.

CWE-1427Improper Neutralization of Input Used for LLM Prompting (opens in a new tab)
Base weakness
The product uses externally-provided data to build prompts provided to large language models (LLMs), but the way these prompts are constructed causes the LLM to fail to distinguish between user-supplied inputs and developer provided system directives.
Architecture and Design
LLM-enabled applications should be designed to ensure proper sanitization of user-controllable input, ensuring that no intentionally misleading or dangerous characters can be included.
Implementation
LLM prompts should be constructed in a way that effectively differentiates between user-supplied input and developer-constructed system prompting to reduce the chance of model confusion at inference-time.
Architecture and Design
LLM-enabled applications should be designed to ensure proper sanitization of user-controllable input, ensuring that no intentionally misleading or dangerous characters can be included.
OWASP Cheat Sheets
Abuse Case (opens in a new tab)
Deserialization (opens in a new tab)
OWASP ASVS 4.0.3
V1.5.1 (opens in a new tab)
From MITRE CWE, MITRE CAPEC and OWASP (Top 10, OpenCRE).

References

help.salesforce.com/s/articleView?id=005228032&type=1 (opens in a new tab)

Community reviews

Loading reviews…

Exploitation evidence

What to do

Affected software

Description

AI analysisMachine-generated, updated 11 Nov 2025, 18:54 UTC

WeaknessesCWE-1427

Technical details

References

Community reviews

Related threats