CVE-2024-10950: Improper Control of Generation of Code

In binary-husky/gptacademic version = 3.83, the plugin CodeInterpreter is vulnerable to code injection caused by prompt injection. The root cause is the execution of user-provided prompts that generate untrusted code without a sandbox, allowing the execution of parts of the LLM-generated code. Th...

CVE-2024-12911: Improper Neutralization of Special Elements used in an SQL Command

A vulnerability in the defaultjsonalyzer function of the JSONalyzeQueryEngine in the run-llama/llamaindex repository allows for SQL injection via prompt injection. This can lead to arbitrary file creation and Denial-of-Service DoS attacks. The vulnerability affects the latest version and is fixed...

Announcing the winners of the Adaptive Prompt Injection Challenge (LLMail-Inject)

We are excited to announce the winners of LLMail-Inject, our first Adaptive Prompt Injection Challenge! The challenge ran from December 2024 until February 2025 and was featured as one of the four official competitions of the 3rd IEEE Conference on Secure and Trustworthy Machine Learning IEEE...

BIT-GITLAB-2024-3303 Improper Neutralization of Input Used for LLM Prompting in GitLab

An issue was discovered in GitLab EE affecting all versions starting from 16.0 prior to 17.6.5, starting from 17.7 prior to 17.7.4, and starting from 17.8 prior to 17.8.2, which allows an attacker to exfiltrate contents of a private issue using prompt injection...

CVE-2024-3303

An issue was discovered in GitLab EE affecting all versions starting from 16.0 prior to 17.6.5, starting from 17.7 prior to 17.7.4, and starting from 17.8 prior to 17.8.2, which allows an attacker to exfiltrate contents of a private issue using prompt injection...

CVE-2024-12366

PandasAI uses an interactive prompt function that is vulnerable to prompt injection and run arbitrary Python code that can lead to Remote Code Execution RCE instead of the intended explanation of the natural language processing by the LLM...

CVE-2024-3303

An issue was discovered in GitLab EE affecting all versions starting from 16.0 prior to 17.6.5, starting from 17.7 prior to 17.7.4, and starting from 17.8 prior to 17.8.2, which allows an attacker to exfiltrate contents of a private issue using prompt injection...

UBUNTU-CVE-2024-3303

An issue was discovered in GitLab EE affecting all versions starting from 16.0 prior to 17.6.5, starting from 17.7 prior to 17.7.4, and starting from 17.8 prior to 17.8.2, which allows an attacker to exfiltrate contents of a private issue using prompt injection...

CVE-2024-3303 Improper Neutralization of Input Used for LLM Prompting in GitLab

An issue was discovered in GitLab EE affecting all versions starting from 16.0 prior to 17.6.5, starting from 17.7 prior to 17.7.4, and starting from 17.8 prior to 17.8.2, which allows an attacker to exfiltrate contents of a private issue using prompt injection...

CVE-2024-3303

CVE-2024-3303 affects GitLab Enterprise Edition (GitLab EE) — all versions from 16.0 up to 17.6.5, from 17.7 up to 17.7.4, and from 17.8 up to 17.8.2. The issue allows an attacker to exfiltrate contents of a private issue via prompt injection. The description and connected documents confirm the a...

CVE-2024-3303 Improper Neutralization of Input Used for LLM Prompting in GitLab

An issue was discovered in GitLab EE affecting all versions starting from 16.0 prior to 17.6.5, starting from 17.7 prior to 17.7.4, and starting from 17.8 prior to 17.8.2, which allows an attacker to exfiltrate contents of a private issue using prompt injection...

CVE-2024-3303 Improper Neutralization of Input Used for LLM Prompting in GitLab

An issue was discovered in GitLab EE affecting all versions starting from 16.0 prior to 17.6.5, starting from 17.7 prior to 17.7.4, and starting from 17.8 prior to 17.8.2, which allows an attacker to exfiltrate contents of a private issue using prompt injection...

Prompt Injection

pandasai is vulnerable to Prompt Injection. The vulnerability is due to insufficient input validation in the interactive prompt function, allowing prompt injection to execute arbitrary Python code...

GitLab Enterprise Edition 安全漏洞

GitLab Enterprise Edition EE is a content management system from GitLab, Inc. in the United States. A security vulnerability exists in GitLab Enterprise Edition that stems from a prompt injection leading to private content disclosure...

CVE-2024-3303: Undefined Security Weakness

An issue was discovered in GitLab EE affecting all versions starting from 16.0 prior to 17.6.5, starting from 17.7 prior to 17.7.4, and starting from 17.8 prior to 17.8.2, which allows an attacker to exfiltrate contents of a private issue using prompt injection...

PT-2025-6643 · Gitlab · Gitlab Ce/Ee

Name of the Vulnerable Software and Affected Versions: GitLab EE versions 16.0 through 17.6.5 GitLab EE versions 17.7 through 17.7.4 GitLab EE versions 17.8 through 17.8.2 Description: An issue was discovered in GitLab EE which allows an attacker to exfiltrate contents of a private issue using...

PandasAI interactive prompt function Remote Code Execution (RCE)

PandasAI uses an interactive prompt function that is vulnerable to prompt injection and run arbitrary Python code that can lead to Remote Code Execution RCE instead of the intended explanation of the natural language processing by the LLM. The security controls of PandasAI 2.4.3 and earlier fail ...

GHSA-VV2H-2W3Q-3FX7 PandasAI interactive prompt function Remote Code Execution (RCE)

PandasAI uses an interactive prompt function that is vulnerable to prompt injection and run arbitrary Python code that can lead to Remote Code Execution RCE instead of the intended explanation of the natural language processing by the LLM. The security controls of PandasAI 2.4.3 and earlier fail ...

CVE-2024-12366

PandasAI uses an interactive prompt function that is vulnerable to prompt injection and run arbitrary Python code that can lead to Remote Code Execution RCE instead of the intended explanation of the natural language processing by the LLM...

CVE-2024-12366 CVE-2024-12366

PandasAI uses an interactive prompt function that is vulnerable to prompt injection and run arbitrary Python code that can lead to Remote Code Execution RCE instead of the intended explanation of the natural language processing by the LLM...