Which versions of letta are affected by EUVD-2025-18359?

Organizations using letta-ai letta should be aware of moderate risk from CVE-2025-6101, a code injection vulnerability rated CVSS 5.5.

How to fix or mitigate EUVD-2025-18359?

Within 30 days: Identify affected systems running letta-ai letta and apply vendor patches as part of regular patch cycle. Validate input sanitization for user-controlled parameters.

letta EUVD-2025-18359

Q: What is the CVSS score of EUVD-2025-18359?

EUVD-2025-18359 has a CVSS 4.0 base score of 2.0 (Low). CVSS vector: CVSS:4.0/AV:A/AC:L/AT:N/PR:L/UI:N/VC:L/VI:L/VA:L/SC:N/SI:N/SA:N/E:P/CR:X/IR:X/AR:X/MAV:X/MAC:X/MAT:X/MPR:X/MUI:X/MVC:X/MVI:X/MVA:X/MSC:X/MSI:X/MSA:X/S:X/AU:X/R:X/V:X/RE:X/U:X. EPSS exploitation probability: 0.0%.

| CVE-2025-6101 LOW

Code Injection (CWE-94)

2025-06-16 cna@vuldb.com

RCE Code Injection

2.0

CVSS 4.0 · NVD

Severity by source

NVD PRIMARY

2.0 LOW

CVSS:4.0/AV:A/AC:L/AT:N/PR:L/UI:N/VC:L/VI:L/VA:L/SC:N/SI:N/SA:N/E:P/CR:X/IR:X/AR:X/MAV:X/MAC:X/MAT:X/MPR:X/MUI:X/MVC:X/MVI:X/MVA:X/MSC:X/MSI:X/MSA:X/S:X/AU:X/R:X/V:X/RE:X/U:X

vuln.today AI

5.5 MEDIUM

Adjacent network access and low privileges required, with limited impact on all security dimensions.

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

4.0 AV:A/AC:L/AT:N/PR:L/UI:N/VC:L/VI:L/VA:L/SC:N/SI:N/SA:N

Primary rating from NVD.

CVSS VectorNVD

Attack Vector

Adjacent

Attack Complexity

Low

Privileges Required

Low

User Interaction

None

Scope

Lifecycle Timeline

Severity Changed

Apr 29, 2026 - 01:11 NVD

MEDIUM LOW

CVSS changed

Apr 29, 2026 - 01:11 NVD

5.5 (MEDIUM) 2.0 (LOW)

EUVD ID Assigned

Mar 14, 2026 - 21:59 euvd

EUVD-2025-18359

Analysis Generated

Mar 14, 2026 - 21:59 vuln.today

CVE Published

Jun 16, 2025 - 03:15 nvd

MEDIUM 5.5

DescriptionCVE.org

A vulnerability classified as critical has been found in letta-ai letta up to 0.4.1. Affected is the function function_message of the file letta/letta/interface.py. The manipulation of the argument function_name/function_args leads to improper neutralization of directives in dynamically evaluated code. The exploit has been disclosed to the public and may be used.

AnalysisAI

Code injection vulnerability in letta-ai letta up to version 0.4.1 allows authenticated adjacent network attackers to execute arbitrary Python code by manipulating the function_name or function_args arguments in the function_message method. Public exploit code exists, but no active exploitation has been confirmed by CISA.

Technical ContextAI

The vulnerability exists in the function_message function within letta/letta/interface.py of the letta-ai letta Python library, which facilitates LLM agent interactions. The root cause is improper neutralization of directives in dynamically evaluated code (CWE-94), likely due to use of eval() or exec() on user-supplied function_name and function_args without sanitization. Impacted versions are specifically 0.4.0 and 0.4.1 of the letta package.

RemediationAI

No official patch has been released at the time of analysis. Monitor the GitHub issue #2613 for a fix and upgrade to a patched version as soon as one is available. As a temporary workaround, restrict network access to the letta interface to trusted hosts only, as the attack requires adjacent network connectivity. Additionally, ensure that only highly trusted users hold low-privilege accounts, and consider disabling the dynamic function evaluation feature if feasible until an update is applied. These measures may limit exploitability but do not fully eliminate the risk.