CVE-2024-7962: Path Traversal: '\..\filename'

An arbitrary file read vulnerability exists in gaizhenbiao/chuanhuchatgpt version 20240628 due to insufficient validation when loading prompt template files. An attacker can read any file that matches specific criteria using an absolute path. The file must not have a .json extension and, except f...

LangChain SQL注入漏洞

LangChain is a LangChain open source framework for developing applications powered by the Large Language Model LLM. A SQL injection vulnerability exists in LangChain version 0.2.5, which stems from SQL injection that can be achieved via prompt injection and could lead to unauthorized data...

Lunary 安全漏洞

Lunary is a production toolkit for LLMs open sourced by Lunary. A security vulnerability exists in Lunary v1.3.2, which stems from the presence of an IDOR vulnerability that allows an authenticated user to update another user's prompt by manipulating the id parameter in the request...

CVE-2024-8309: Improper Neutralization of Special Elements used in an SQL Command

A vulnerability in the GraphCypherQAChain class of langchain-ai/langchain version 0.2.5 allows for SQL injection through prompt injection. This vulnerability can lead to unauthorized data manipulation, data exfiltration, denial of service DoS by deleting all data, breaches in multi-tenant securit...

PT-2024-38718 · Unknown · Gaizhenbiao/Chuanhuchatgpt

Name of the Vulnerable Software and Affected Versions: gaizhenbiao/chuanhuchatgpt version 20240628 Description: An arbitrary file read issue exists due to insufficient validation when loading prompt template files. An attacker can read any file that matches specific criteria using an absolute pat...

Security Vulnerabilities fixed in Thunderbird 128.4 — Mozilla

A permission leak could have occurred from a trusted site to an untrusted site via embed or object elements. An attacker could have caused a use-after-free when accessibility was enabled, leading to a potentially exploitable crash. The origin of an external protocol handler prompt could have been...

Mozilla Firefox ESR < 128.4

The version of Firefox ESR installed on the remote Windows host is prior to 128.4. It is, therefore, affected by multiple vulnerabilities as referenced in the mfsa2024-56 advisory. - Memory safety bugs present in Firefox 131, Firefox ESR 128.3, and Thunderbird 128.3. Some of these bugs showed...

CVE-2024-7042: Improper Neutralization of Special Elements used in an SQL Command

A vulnerability in the GraphCypherQAChain class of langchain-ai/langchainjs versions 0.2.5 and all versions with this class allows for prompt injection, leading to SQL injection. This vulnerability permits unauthorized data manipulation, data exfiltration, denial of service DoS by deleting all...

PT-2024-38042

Name of the Vulnerable Software and Affected Versions langchain-ai/langchainjs versions 0.2.5 and later Description The issue allows for prompt injection, leading to SQL injection, which can result in unauthorized data manipulation, data exfiltration, denial of service DoS by deleting all data,...

CVE-2024-7473: Authorization Bypass Through User-Controlled Key

An IDOR vulnerability exists in the 'Evaluations' function of the 'umgws datasets' section in lunary-ai/lunary versions 1.3.2. This vulnerability allows an authenticated user to update other users' prompts by manipulating the 'id' parameter in the request. The issue is fixed in version 1.4.3...

CVE-2024-48144

A prompt injection vulnerability in the chatbox of Fusion Chat Chat AI Assistant Ask Me Anything v1.2.4.0 allows attackers to access and exfiltrate all previous and subsequent chat data between the user and the AI assistant via a crafted message...

CVE-2024-48140

A prompt injection vulnerability in the chatbox of Butterfly Effect Limited Monica Your AI Copilot powered by ChatGPT4 v6.3.0 allows attackers to access and exfiltrate all previous and subsequent chat data between the user and the AI assistant via a crafted message...

CVE-2024-48145

A prompt injection vulnerability in the chatbox of Netangular Technologies ChatNet AI Version v1.0 allows attackers to access and exfiltrate all previous and subsequent chat data between the user and the AI assistant via a crafted message...

CVE-2024-48141

A prompt injection vulnerability in the chatbox of Zhipu AI CodeGeeX v2.17.0 allows attackers to access and exfiltrate all previous and subsequent chat data between the user and the AI assistant via a crafted message...

Fusion Chat AI Assistant 安全漏洞

Fusion Chat AI Assistant is an AI bot from Fusion Chat, Inc. A security vulnerability exists in Fusion Chat AI Assistant version v1.2.4.0, which stems from a prompt injection vulnerability in the chat box that allows an attacker to access and disclose all previous and subsequent chat data between...

PT-2024-33004 · Unknown · Fusion Chat Chat Ai Assistant

Name of the Vulnerable Software and Affected Versions: Fusion Chat Chat AI Assistant Ask Me Anything version 1.2.4.0 Description: A prompt injection issue in the chatbox allows attackers to access and exfiltrate all previous and subsequent chat data between the user and the AI assistant via a...

CVE-2024-48145

Netangular Technologies ChatNet AI Version v1.0 is vulnerable to a prompt injection flaw within its chatbox. An attacker can use a crafted message to gain unauthorized access to and exfiltrate all previous and subsequent chat data exchanged between a user and the AI assistant. No specific remedia...

CVE-2024-48145

A prompt injection vulnerability in the chatbox of Netangular Technologies ChatNet AI Version v1.0 allows attackers to access and exfiltrate all previous and subsequent chat data between the user and the AI assistant via a crafted message...

CVE-2024-48139

The AI coding assistant Blackbox AI version 1.3.95 is vulnerable to a prompt injection attack within its chatbox. By sending a crafted message , an attacker can access and exfiltrate all previous and subsequent chat data exchanged between a user and the AI assistant. At this time, no patched vers...

CVE-2024-48144: Improper Neutralization of Special Elements used in a Command

A prompt injection vulnerability in the chatbox of Fusion Chat Chat AI Assistant Ask Me Anything v1.2.4.0 allows attackers to access and exfiltrate all previous and subsequent chat data between the user and the AI assistant via a crafted message...