PT-2024-37188

Name of the Vulnerable Software and Affected Versions: vanna-ai/vanna affected versions not specified Description: The issue is related to remote code execution due to prompt injection in the vanna.ask function. This is caused by the lack of a sandbox when executing LLM-generated code, allowing a...

Prompt Injection

Vanna is vulnerable to Prompt Injection. The vulnerability is due to improper input validation in the Vanna library's "ask" method, when allowing external input with "visualize" set to True, which allows a user to execute arbitrary python code...

New EmailGPT Flaw Puts User Data at Risk: Remove the Extension NOW

Synopsys warns of a new prompt injection hack involving a security vulnerability in EmailGPT, a popular AI email…...

CVE-2024-5184

The EmailGPT service contains a prompt injection vulnerability. The service uses an API service that allows a malicious user to inject a direct prompt and take over the service logic. Attackers can exploit the issue by forcing the AI service to leak the standard hard-coded system prompts and/or...

CVE-2024-5184 Prompt Injection in EmailGPT

The EmailGPT service contains a prompt injection vulnerability. The service uses an API service that allows a malicious user to inject a direct prompt and take over the service logic. Attackers can exploit the issue by forcing the AI service to leak the standard hard-coded system prompts and/or...

CVE-2024-5184 Prompt Injection in EmailGPT

The EmailGPT service contains a prompt injection vulnerability. The service uses an API service that allows a malicious user to inject a direct prompt and take over the service logic. Attackers can exploit the issue by forcing the AI service to leak the standard hard-coded system prompts and/or...

CVE-2024-5184

CVE-2024-5184 affects the EmailGPT service. The vulnerability is a prompt injection flaw in the service’s API, enabling a malicious user to inject prompts and take over service logic. Exploitation can force leakage of hard-coded system prompts and/or execution of unwanted prompts, with attacks po...

CVE-2024-5184: Improper Neutralization of Special Elements in Output Used by a Downstream Component

The EmailGPT service contains a prompt injection vulnerability. The service uses an API service that allows a malicious user to inject a direct prompt and take over the service logic. Attackers can exploit the issue by forcing the AI service to leak the standard hard-coded system prompts and/or...

EmailGPT Security Vulnerabilities

EmailGPT is a Google Chrome extension by individual developer Nasrullah in Singapore that helps users compose emails in Gmail using OpenAI's GPT-3.5 model. A security vulnerability exists in EmailGPT that stems from the inclusion of a prompt injection vulnerability...

PT-2024-34967 · Emailgpt · Emailgpt

Name of the Vulnerable Software and Affected Versions: EmailGPT affected versions not specified Description: The EmailGPT service contains a prompt injection vulnerability. The service uses an API service that allows a malicious user to inject a direct prompt and take over the service logic...

AI jailbreaks: What they are and how they can be mitigated

Generative AI systems are made up of multiple components that interact to provide a rich user experience between the human and the AI models. As part of a responsible AI approach, AI models are protected by layers of defense mechanisms to prevent the production of harmful content or being used to...

GHSA-7735-W2JP-GVG6 Vanna prompt injection code execution

The Vanna library uses a prompt function to present the user with visualized results, it is possible to alter the prompt using prompt injection and run arbitrary Python code instead of the intended visualization code. Specifically - allowing external input to the library’s “ask” method with...

Vanna prompt injection code execution

The Vanna library uses a prompt function to present the user with visualized results, it is possible to alter the prompt using prompt injection and run arbitrary Python code instead of the intended visualization code. Specifically - allowing external input to the library’s “ask” method with...

CVE-2024-5565

The Vanna library uses a prompt function to present the user with visualized results, it is possible to alter the prompt using prompt injection and run arbitrary Python code instead of the intended visualization code. Specifically - allowing external input to the library’s “ask” method with...

CVE-2024-5565

The Vanna library uses a prompt function to present the user with visualized results, it is possible to alter the prompt using prompt injection and run arbitrary Python code instead of the intended visualization code. Specifically - allowing external input to the library’s “ask” method with...

CVE-2024-5565 Prompt Injection in "ask" API with visualization leads to RCE

The Vanna library uses a prompt function to present the user with visualized results, it is possible to alter the prompt using prompt injection and run arbitrary Python code instead of the intended visualization code. Specifically - allowing external input to the library’s “ask” method with...

CVE-2024-5565 Prompt Injection in "ask" API with visualization leads to RCE

The Vanna library uses a prompt function to present the user with visualized results, it is possible to alter the prompt using prompt injection and run arbitrary Python code instead of the intended visualization code. Specifically - allowing external input to the library’s “ask” method with...

CVE-2024-5565: Improper Control of Generation of Code

The Vanna library uses a prompt function to present the user with visualized results, it is possible to alter the prompt using prompt injection and run arbitrary Python code instead of the intended visualization code. Specifically - allowing external input to the library’s “ask” method with...

PT-2024-36568

Name of the Vulnerable Software and Affected Versions Vanna library affected versions not specified Description The Vanna library is affected by a remote code execution issue due to prompt injection. This allows an attacker to alter the prompt function used for visualized results and run arbitrar...

LLMs’ Data-Control Path Insecurity

Back in the 1960s, if you played a 2,600Hz tone into an AT&T pay phone, you could make calls without paying. A phone hacker named John Draper noticed that the plastic whistle that came free in a box of Captain Crunch cereal worked to make the right sound. That became his hacker name, and everyone...