CVE-2026-3989
CVE-2026-3989
Description
SGLangs `replay_request_dump.py` contains an insecure pickle.load() without validation and proper deserialization. An attacker can take advantage of this by providing a malicious .pkl file, which will execute the attackers code on the device running the script.
INFO
Published Date :
March 12, 2026, 12:15 p.m.
Last Modified :
March 16, 2026, 7:16 p.m.
Remotely Exploit :
No
Source :
[email protected]
CVSS Scores
| Score | Version | Severity | Vector | Exploitability Score | Impact Score | Source |
|---|---|---|---|---|---|---|
| CVSS 3.1 | HIGH | 134c704f-9b21-4f2e-91b3-4a467353bcc0 |
Solution
- Avoid deserializing untrusted data.
- Validate all input data sources.
- Sanitize data before processing.
- Use safer serialization formats.
References to Advisories, Solutions, and Tools
Here, you will find a curated list of external links that provide in-depth
information, practical solutions, and valuable tools related to
CVE-2026-3989.
| URL | Resource |
|---|---|
| https://github.com/sgl-project/sglang/blob/main/scripts/playground/replay_request_dump.py | |
| https://orca.security/resources/blog/sglang-llm-framework-rce-vulnerabilities/ |
CWE - Common Weakness Enumeration
While CVE identifies
specific instances of vulnerabilities, CWE categorizes the common flaws or
weaknesses that can lead to vulnerabilities. CVE-2026-3989 is
associated with the following CWEs:
Common Attack Pattern Enumeration and Classification (CAPEC)
Common Attack Pattern Enumeration and Classification
(CAPEC)
stores attack patterns, which are descriptions of the common attributes and
approaches employed by adversaries to exploit the CVE-2026-3989
weaknesses.
We scan GitHub repositories to detect new proof-of-concept exploits. Following list is a collection of public exploits and proof-of-concepts, which have been published on GitHub (sorted by the most recently updated).
Results are limited to the first 15 repositories due to potential performance issues.
The following list is the news that have been mention
CVE-2026-3989 vulnerability anywhere in the article.
-
The Hacker News
AI Flaws in Amazon Bedrock, LangSmith, and SGLang Enable Data Exfiltration and RCE
Cybersecurity researchers have disclosed details of a new method for exfiltrating sensitive data from artificial intelligence (AI) code execution environments using domain name system (DNS) queries. I ... Read more
-
Daily CyberSecurity
The Poisoned Pickle: Critical Unpatched RCE Flaws Expose SGLang AI Infrastructure
Security researchers have issued a warning to the AI development community following the discovery of critical vulnerabilities in SGLang, a popular open-source serving framework for Large Language Mod ... Read more
The following table lists the changes that have been made to the
CVE-2026-3989 vulnerability over time.
Vulnerability history details can be useful for understanding the evolution of a vulnerability, and for identifying the most recent changes that may impact the vulnerability's severity, exploitability, or other characteristics.
-
CVE Modified by 134c704f-9b21-4f2e-91b3-4a467353bcc0
Mar. 16, 2026
Action Type Old Value New Value Added CVSS V3.1 AV:L/AC:L/PR:N/UI:R/S:U/C:H/I:H/A:H -
New CVE Received by [email protected]
Mar. 12, 2026
Action Type Old Value New Value Added Description SGLangs `replay_request_dump.py` contains an insecure pickle.load() without validation and proper deserialization. An attacker can take advantage of this by providing a malicious .pkl file, which will execute the attackers code on the device running the script. Added Reference https://github.com/sgl-project/sglang/blob/main/scripts/playground/replay_request_dump.py Added Reference https://orca.security/resources/blog/sglang-llm-framework-rce-vulnerabilities/