CVE-2024-4099

Removed by vendor...

CVE-2024-45989

Monica AI Assistant desktop application v2.3.0 is vulnerable to Exposure of Sensitive Information to an Unauthorized Actor. A prompt injection allows an attacker to modify chatbot answer with an unloaded image that exfiltrates the user's sensitive chat data of the current session to a malicious...

PT-2024-31874 · Unknown · Monica Ai Assistant

Name of the Vulnerable Software and Affected Versions: Monica AI Assistant desktop application version 2.3.0 Description: The issue allows an attacker to modify the chatbot's answer with an unloaded image, which can exfiltrate the user's sensitive chat data of the current session to a malicious...

CVE-2024-45989

Monica AI Assistant desktop application v2.3.0 is vulnerable to Exposure of Sensitive Information to an Unauthorized Actor. A prompt injection allows an attacker to modify chatbot answer with an unloaded image that exfiltrates the user's sensitive chat data of the current session to a malicious...

PT-2024-6709 · Gitlab · Gitlab Ce/Ee +1

Name of the Vulnerable Software and Affected Versions: GitLab EE versions 16.0 through 17.2.7 GitLab EE versions 17.3 through 17.3.3 GitLab EE versions 17.4 through 17.4.0 Description: An issue has been discovered in GitLab EE affecting the AI feature, which reads unsanitized content. This could...

CVE-2024-45989

CVE-2024-45989 affects the Monica AI Assistant desktop application v2.3.0. The vulnerability is a prompt injection that allows an attacker to inject an unloaded image into chatbot answers, enabling exfiltration of the user’s current-session chat data to a malicious third party or attacker-control...

ChatGPT macOS Flaw Could've Enabled Long-Term Spyware via Memory Function

A now-patched security vulnerability in OpenAI's ChatGPT app for macOS could have made it possible for attackers to plant long-term persistent spyware into the artificial intelligence AI tool's memory. The technique, dubbed SpAIware, could be abused to facilitate "continuous data exfiltration of...

BIT-GITLAB-2024-7110 Improper Neutralization of Special Elements used in a Command ('Command Injection') in GitLab

An issue was discovered in GitLab EE affecting all versions starting 17.0 to 17.1.6, 17.2 prior to 17.2.4, and 17.3 prior to 17.3.1 allows an attacker to execute arbitrary command in a victim's pipeline through prompt injection...

CVE-2024-7110

An issue was discovered in GitLab EE affecting all versions starting 17.0 to 17.1.6, 17.2 prior to 17.2.4, and 17.3 prior to 17.3.1 allows an attacker to execute arbitrary command in a victim's pipeline through prompt injection...

CVE-2024-7110

An issue was discovered in GitLab EE affecting all versions starting 17.0 to 17.1.6, 17.2 prior to 17.2.4, and 17.3 prior to 17.3.1 allows an attacker to execute arbitrary command in a victim's pipeline through prompt injection...

UBUNTU-CVE-2024-7110

An issue was discovered in GitLab EE affecting all versions starting 17.0 to 17.1.6, 17.2 prior to 17.2.4, and 17.3 prior to 17.3.1 allows an attacker to execute arbitrary command in a victim's pipeline through prompt injection...

CVE-2024-7110 Improper Neutralization of Special Elements used in a Command ('Command Injection') in GitLab

An issue was discovered in GitLab EE affecting all versions starting 17.0 to 17.1.6, 17.2 prior to 17.2.4, and 17.3 prior to 17.3.1 allows an attacker to execute arbitrary command in a victim's pipeline through prompt injection...

CVE-2024-7110

CVE-2024-7110 affects GitLab EE, spanning all versions 17.0–17.1.6, 17.2 before 17.2.4, and 17.3 before 17.3.1. The issue allows an attacker to execute arbitrary commands in a victim’s pipeline via prompt injection. The available connected documents consistently describe the vulnerability as a co...

CVE-2024-7110

Removed by vendor...

GitLab Enterprise Edition 安全漏洞

GitLab Enterprise Edition EE is a content management system from the American company GitLab. A security vulnerability exists in GitLab Enterprise Edition versions 17.0 through 17.1.6, 17.2 through 17.2.4, and 17.3 through 17.3.1, which stems from an arbitrary command that can be executed via...

GitLab 17.1 < 17.1.6 / 17.2 < 17.2.4 / 17.3 < 17.3.1 (CVE-2024-7110)

The version of GitLab installed on the remote host is affected by a vulnerability, as follows: - An issue was discovered in GitLab EE affecting all versions starting 17.0 to 17.1.6, 17.2 prior to 17.2.4, and 17.3 prior to 17.3.1 allows an attacker to execute arbitrary command in a victim's pipeli...

Gitlab -- vulnerabilities

Gitlab reports: The GitLab Web Interface Does Not Guarantee Information Integrity When Downloading Source Code from Releases Denial of Service by importing maliciously crafted GitHub repository Prompt injection in "Resolve Vulnerabilty" results in arbitrary command execution in victim's pipeline ...

Indirect prompt injection in the real world: how people manipulate neural networks

What is prompt injection? Large language models LLMs – the neural network algorithms that underpin ChatGPT and other popular chatbots – are becoming ever more powerful and inexpensive. For this reason, third-party applications that make use of them are also mushrooming, from systems for document...

De-risk Generative AI: Enterprise TruRisk Platform Advances to Secure AI and LLM Workloads

As we stand at the frontier of technological innovation, artificial intelligence AI and large language models LLMs are reshaping industries, driving automation, enhancing customer experiences, optimizing processes, and unlocking business opportunities for modern enterprises. However, this rapid...

CVE-2024-6331

stitionai/devika main branch as of commit cdfb782b0e634b773b10963c8034dc9207ba1f9f is vulnerable to Local File Read LFI by Prompt Injection. The integration of Google Gimini 1.0 Pro with HarmBlockThreshold.BLOCKNONE for HarmCategory.HARMCATEGORYHATESPEECH and HarmCategory.HARMCATEGORYHARASSMENT i...