CVE-2025-6101
Awaiting Analysis Awaiting Analysis - Queue
BaseFortify

Publication date: 2025-06-16

Last updated on: 2026-04-29

Assigner: VulDB

Description
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.
CVSS Scores
EPSS Scores
Probability:
Percentile:
Meta Information
Published
2025-06-16
Last Modified
2026-04-29
Generated
2026-05-07
AI Q&A
2025-06-16
EPSS Evaluated
2026-05-05
NVD
Affected Vendors & Products
Currently, no data is known.
Helpful Resources
Exploitability
CWE
CWE Icon
KEV
KEV Icon
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.
CWE-95 The product receives input from an upstream component, but it does not neutralize or incorrectly neutralizes code syntax before using the input in a dynamic evaluation call (e.g. "eval").
Attack-Flow Graph
AI Powered Q&A
Can you explain this vulnerability to me?

CVE-2025-6101 is a code injection vulnerability in the letta-ai letta software (up to version 0.4.1) caused by the use of Python's eval() function in the function_message function. This function processes input strings and extracts function_name and function_args. For certain function_name values, function_args is executed using eval() without proper sanitization, allowing an attacker controlling the input to inject and execute arbitrary Python code. This can lead to unauthorized system access, data leakage, or other security risks. [1, 2, 3]


How can this vulnerability impact me? :

This vulnerability can lead to arbitrary code execution on the affected system, which may result in unauthorized system access, data leakage, destruction of data, or other severe security impacts. An attacker can execute malicious commands, potentially compromising the confidentiality, integrity, and availability of the system. [1, 2, 3]


How can this vulnerability be detected on my network or system? Can you suggest some commands?

This vulnerability can be detected by monitoring for suspicious input strings to the letta-ai letta application, specifically those starting with "Running " followed by function calls that use eval() on function_args. You can search logs or network traffic for patterns like "Running archival_memory_insert" or other vulnerable function names. Additionally, you can check the source code for the presence of eval() calls in letta/letta/interface.py around lines 199 and 225. Example commands to detect suspicious activity include using grep to find exploit attempts in logs: `grep -E 'Running (archival_memory_insert|archival_memory_search|core_memory_replace|core_memory_append|conversation_search|conversation_search_date)' /path/to/logs` or monitoring network traffic for such patterns. Also, scanning the codebase for eval usage: `grep -n 'eval(' letta/letta/interface.py`. [1, 2]


What immediate steps should I take to mitigate this vulnerability?

Immediate mitigation steps include disabling or restricting the use of the vulnerable letta-ai letta versions up to 0.4.1, as no known countermeasures or patches are currently available. Avoid processing untrusted input that triggers the vulnerable eval() calls. If possible, replace the affected software with an alternative product or a patched version once available. Additionally, restrict access to the affected system to trusted users only and monitor for exploitation attempts. Applying strict input validation or removing the use of eval() in the code is recommended but requires code changes. [3]


Ask Our AI Assistant
Need more information? Ask your question to get an AI reply (Powered by our expertise)
0/70
EPSS Chart