PT-2025-30418 · Unknown · Deepfiction Ai

Name of the Vulnerable Software and Affected Versions: Deepfiction AI versions prior to June 3, 2025 Description: An Insecure Direct Object Reference IDOR vulnerability exists in Deepfiction AI. This allows attackers to access and utilize other users' credits for interacting with the Large Langua...

CVE-2025-51867

Insecure Direct Object Reference IDOR vulnerability in Deepfiction AI deepfiction.ai thru June 3, 2025, allowing attackers to chat with the LLM using other users' credits via sensitive information gained by the /browse/stories endpoint...

Letta-ai letta 代码注入漏洞

Letta-ai letta is a stateful agent framework with memory, inference, and context management from the Letta-ai open source. A security vulnerability exists in Letta-ai letta version 0.7.12, which originates in the /v1/tools/run endpoint and allows the execution of arbitrary Python code and system...

A week in security (July 14 – July 20)

Last week on Malwarebytes Labs: Meta execs pay the pain away with $8 billion privacy settlement Adoption agency leaks over a million records Meta AI chatbot bug could have allowed anyone to see private conversations WeTransfer walks back clause that said it would train AI on your files Chrome fix...

EncryptHub Targets Web3 Developers Using Fake AI Platforms to Deploy Fickle Stealer Malware

The financially motivated threat actor known as EncryptHubaka LARVA-208 and Water Gamayun has been attributed to a new campaign that's targeting Web3 developers to infect them with information stealer malware. "LARVA-208 has evolved its tactics, using fake AI platforms e.g., Norlax AI, mimicking...

CVE-2025-7883

A vulnerability classified as critical has been found in Eluktronics Control Center 5.23.51.41. Affected is an unknown function of the file \AiStoneService\MyControlCenter\Command of the component Powershell Script Handler. The manipulation leads to command injection. Attacking locally is a...

CVE-2025-50708

An issue in Perplexity AI GPT-4 v.2.51.0 allows a remote attacker to obtain sensitive information via the token component in the shared chat URL...

CVE-2025-53928

MaxKB is an open-source AI assistant for enterprise. Prior to versions 1.10.9-lts and 2.0.0, a Remote Command Execution vulnerability exists in the MCP call. Versions 1.10.9-lts and 2.0.0 fix the issue...

CVE-2025-50708

An issue in Perplexity AI GPT-4 v.2.51.0 allows a remote attacker to obtain sensitive information via the token component in the shared chat URL...

Microsoft at Black Hat USA 2025: A unified approach to modern cyber defense

Microsoft will be at Black Hat USA 2025, August 5–7 in Las Vegas, and we’re bringing you a unified, practitioner-driven experience built around real-world insights, threat intelligence, incident response, and hands-on AI expertise. We believe security teams are strongest when intelligence, tools,...

Critical NVIDIA Container Toolkit Flaw Allows Privilege Escalation on AI Cloud Services

Cybersecurity researchers have disclosed a critical container escape vulnerability in the NVIDIA Container Toolkit that could pose a severe threat to managed AI cloud services. The vulnerability, tracked as CVE-2025-23266, carries a CVSS score of 9.0 out of 10.0. It has been codenamed NVIDIAScape...

OAuth Dynamic Client Registration Permissive Metadata Field

OAuth Dynamic Client Registration allows for various metadata fields such as 'clientname', 'websiteuri' during the registration process. When the OAuth server accepts permissive values for such fields, such as ones starting with javascript://, an attacker could exploit this to perform Cross-Site...

MCP Server Tool Poisoning

Model Context Protocol MCP Server Tool Poisoning occurs when malicious actors manipulate tool configurations or metadata on a malicious MCP server. This can lead to the execution of unauthorized commands, data corruption, or the deployment of malicious tools. Such vulnerabilities are particularly...

PT-2025-30092 · Unknown · Perplexity Ai Gpt-4

Name of the Vulnerable Software and Affected Versions: Perplexity AI GPT-4 version 2.51.0 Description: An issue allows a remote attacker to obtain sensitive information via the token component in the shared chat URL. Recommendations: At the moment, there is no information about a newer version th...

CVE-2025-50708

CVE-2025-50708 affects Perplexity AI GPT-4 v2.51.0. The issue is in the token component of the shared chat URL, enabling a remote attacker to obtain sensitive information (confidentiality impact). CVSS: Network attack vector, low attack complexity, no privileges required, no user interaction, wit...

OAuth Dynamic Client Registration Permissive Redirect URI

OAuth Dynamic Client Registration requires specifying redirect URIs during the registration process. When the OAuth server accepts permissive redirect URIs, such as those allowing arbitrary hosts or ones starting with javascript://, an attacker could exploit this to perform Open Redirect or...

CVE-2025-50708

An issue in Perplexity AI GPT-4 v.2.51.0 allows a remote attacker to obtain sensitive information via the token component in the shared chat URL...

OAuth Dynamic Client Registration Detected

This is an informational plugin to inform the user that the scanner has detected a publicly accessible OAuth Dynamic Client Registration endpoint on the target application. OAuth Dynamic Client Registration allows clients to register dynamically with an authorization server and is very common in...

CVE-2025-50708

An issue in Perplexity AI GPT-4 v.2.51.0 allows a remote attacker to obtain sensitive information via the token component in the shared chat URL...

NVIDIAScape - Critical NVIDIA AI Vulnerability: A Three-Line Container Escape in NVIDIA Container Toolkit (CVE-2025-23266)

New critical vulnerability with 9.0 CVSS presents systemic risk to the AI ecosystem, carries widespread implications for AI infrastructure...