20433 matches found
Prompt Injection 2.0: Hybrid AI Threats
Prompt injection attacks, where malicious input is designed to manipulate AI systems into ignoring their original instructions and following unauthorized commands instead, were first discovered by Preamble, Inc. in May 2022 and responsibly disclosed to OpenAI. Over the last three years, these...
CVE-2024-26293
The Avid Nexis Agent uses a vulnerable gSOAP version. An undocumented vulnerability impacting gSOAP v2.8 makes the application vulnerable to an Unauthenticated Path Traversal vulnerability. This issue affects Avid NEXIS E-series: before 2025.5.1; Avid NEXIS F-series: before 2025.5.1; Avid NEXIS...
MAL-2025-5887 Malicious code in agent-configurator (npm)
--- -= Per source details. Do not edit below this line.=- Source: ghsa-malware 0e65ce26b3c1e446de253231422a7c11c3d90e68dcd8caab1efbdba56150e10a Any computer that has this package installed or running should be considered fully compromised. All secrets and keys stored on that computer should be...
Malicious code in agent-configurator (npm)
--- -= Per source details. Do not edit below this line.=- Source: ghsa-malware 0e65ce26b3c1e446de253231422a7c11c3d90e68dcd8caab1efbdba56150e10a Any computer that has this package installed or running should be considered fully compromised. All secrets and keys stored on that computer should be...
Tenable Agent Elevation of Privilege Vulnerability
Tenable Agent is a vulnerability scanning program from Tenable USA. Tenable Agent has an elevation of privilege vulnerability, which originates from a non-administrative user deleting arbitrary local system files with SYSTEM privileges, and can be exploited by an attacker to tamper with the syste...
Tenable Agent Code Execution Vulnerability
Tenable Agent is a vulnerability scanning program from Tenable USA. Tenable Agent suffers from a code execution vulnerability that originates from a non-administrative user being able to execute code with SYSTEM privileges. No details of the vulnerability are provided at this time...
Unspecified Vulnerability in Tenable Agent
Tenable Agent is a vulnerability scanning program from Tenable USA. Tenable Agent suffers from a security vulnerability that originates from a non-administrative user being able to overwrite arbitrary local system files with SYSTEM privileges. No details of the vulnerability are provided at this...
CVE-2024-26293
The Avid Nexis Agent uses a vulnerable gSOAP version. An undocumented vulnerability impacting gSOAP v2.8 makes the application vulnerable to an Unauthenticated Path Traversal vulnerability. This issue affects Avid NEXIS E-series: before 2025.5.1; Avid NEXIS F-series: before 2025.5.1; Avid NEXIS...
CVE-2024-26291
An Unauthenticated Arbitrary File Read vulnerability affects the Agent when installed on a system. The parameter filename does not validate the path thus allowing users to read arbitrary files. As the application runs with the highest privileges root/NTAUTHORITY SYSTEM by default attackers are ab...
Game Theory Meets LLM and Agentic AI: Reimagining Cybersecurity for the Age of Intelligent Threats
Protecting cyberspace requires not only advanced tools but also a shift in how we reason about threats, trust, and autonomy. Traditional cybersecurity methods rely on manual responses and brittle heuristics. To build proactive and intelligent defense systems, we need integrated theoretical...
MAL-2025-6071 Malicious code in agent-patterns (npm)
The package communicates with a domain associated with malicious activity...
Malicious code in agent-patterns (npm)
The package communicates with a domain associated with malicious activity...
MAL-2025-6114 Malicious code in openai-voice-agent-sdk-sample (npm)
The package communicates with a domain associated with malicious activity...
Malicious code in openai-voice-agent-sdk-sample (npm)
The package communicates with a domain associated with malicious activity...
Security update for rust-keylime
This update for rust-keylime fixes the following issues: CVE-2024-12224: idna: Fixed improper validation in punycode bsc1243861 Update to version 0.2.7+70: builddeps: bump wiremock from 0.6.2 to 0.6.3 builddeps: bump uuid from 1.16.0 to 1.17.0 lib: Introduce AgentIdentity structure gitignore: Add...
OPA server Data API HTTP path injection of Rego
...
The Dark Side of LLMs Agent-Based Attacks for Complete Computer Takeover
The rapid adoption of Large Language Model LLM agents and multi-agent systems enables unprecedented capabilities in natural language processing and generation. However, these systems have introduced unprecedented security vulnerabilities that extend beyond traditional prompt injection attacks. Th...
The vulnerability of the data collection tool for Azure Monitor Agents, which operates on virtual machines and physical servers, stems from improper code generation. This allows attackers to execute arbitrary code.
Vulnerability of the data collection tool for Azure Monitor Agent, which processes virtual machines and physical servers, due to improper code generation management. Exploiting this vulnerability could allow a malicious actor to execute arbitrary code remotely...