CVE Details
Basic Information
| Title | letta-ai letta interface.py function_message eval injection |
|---|---|
| Type | cve |
| Published | 2025-06-16T02:00:11.764Z |
| Last Seen |
Product Information
| Vendor | letta-ai |
|---|---|
| Product | letta |
| Version | 0.4.0 |
CVSS Information
| Base Score | 5.1 (MEDIUM) |
|---|---|
| Attack 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 |
| Confidentiality Impact | |
| Integrity Impact | |
| Availability Impact |
AI Analysis
| AI Description | A critical vulnerability in letta-ai letta up to version 0.4.1 allows remote attackers to execute arbitrary code via the function_message in interface.py due to improper neutralization of directives in dynamically evaluated code. |
|---|---|
| AI Severity | Medium |
| Vendor | letta-ai |
| Product | letta |
| Affected Version | <=0.4.1 |
Affected Products
- letta-ai letta 0.4.0
- letta-ai letta 0.4.1
Additional Information
| CVE List | |
|---|---|
| CWE List | CWE-95, CWE-94 |
| Bulletin Family |
References
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.