Directory Traversal

Overview praisonaiagents is a Praison AI agents for completing complex tasks with Self Reflection Agents Affected versions of this package are vulnerable to Directory Traversal in the MultiAgentLedger and MultiAgentMonitor components. An attacker can access sensitive context data belonging to oth...

Arbitrary Code Injection

Overview praisonaiagents is a Praison AI agents for completing complex tasks with Self Reflection Agents Affected versions of this package are vulnerable to Arbitrary Code Injection via the executecode function. An attacker can gain unauthorized access to the host environment, execute arbitrary...

Deserialization of Untrusted Data

Overview praisonaiagents is a Praison AI agents for completing complex tasks with Self Reflection Agents Affected versions of this package are vulnerable to Deserialization of Untrusted Data through the YAML deserialization in the loadAgentFromFile function. An attacker can execute arbitrary code...

Zammad 安全漏洞

Zammad is a ticketing management software developed by the German company Zammad. Versions of Zammad prior to 7.0.1 contained security vulnerabilities; these vulnerabilities were due to server-side template injection, which could potentially allow remote code execution through AI agents...

SkillTrojan: Backdoor Attacks on Skill-Based Agent Systems

Skill-based agent systems tackle complex tasks by composing reusable skills, improving modularity and scalability while introducing a largely unexamined security attack surface. We propose SkillTrojan, a backdoor attack that targets skill implementations rather than model parameters or training...

CVE-2026-35449

WWBN AVideo is an open source video platform. In versions 26.0 and prior, the install/test.php diagnostic script has its CLI-only access guard disabled by commenting out the die statement. The script remains accessible via HTTP after installation, exposing video viewer statistics including IP...

CVE-2026-5374

An issue that allowed MCP agents to access remediation and asset information from outside of the authorized organization scope has been resolved. This is an instance of CWE-863: Incorrect Authorization, and has an estimated CVSS score of CVSS:3.1/AV:N/AC:H/PR:H/UI:N/S:C/C:H/I:N/A:N 5.8 Medium. Th...

CVE-2026-5379

The CVE-2026-5379 issue affects the runZero Platform (MCP certification workflow). It describes a vulnerability where MCP agents could access certificate information outside their authorized organization scope due to improper authorization (CWE-863). The documented impact is low (CVSS v3.1: 3.0) ...

CVE-2026-5379

An issue that allowed MCP agents to access certificate information from outside of their authorized organization scope has been resolved. This is an instance of CWE-863: Incorrect Authorization, and has an estimated CVSS score of CVSS:3.1/AV:N/AC:H/PR:H/UI:N/S:C/C:L/I:N/A:N 3.0 Low. This issue wa...

CVE-2026-5374 runZero Platform MCP information leak

An issue that allowed MCP agents to access remediation and asset information from outside of the authorized organization scope has been resolved. This is an instance of CWE-863: Incorrect Authorization, and has an estimated CVSS score of CVSS:3.1/AV:N/AC:H/PR:H/UI:N/S:C/C:H/I:N/A:N 5.8 Medium. Th...

CVE-2026-5374

CVE-2026-5374 affects the runZero Platform MCP component. The issue is due to Incorrect Authorization that allowed MCP agents to access remediation and asset information outside the authorized scope, exposing confidentiality. The CVSS v3.1 vector is AV:N/AC:H/PR:H/UI:N/S:C/C:H/I:N/A:N with a base...

CVE-2026-5374

An issue that allowed MCP agents to access remediation and asset information from outside of the authorized organization scope has been resolved. This is an instance of CWE-863: Incorrect Authorization, and has an estimated CVSS score of CVSS:3.1/AV:N/AC:H/PR:H/UI:N/S:C/C:H/I:N/A:N 5.8 Medium. Th...

AI Agents and Non-Human Identities Creating Critical Security Gaps, Report

New research from Keeper Security, reveals non-human identities and automated system-to-system interactions are becoming the top security risk for businesses in 2026...

Benchmarking-Agent-Architectures

Benchmarking Agent Architectures for LLM-Based Exploit Gener...

CVE-2026-5379: Incorrect Authorization

An issue that allowed MCP agents to access certificate information from outside of their authorized organization scope has been resolved. This is an instance of CWE-863: Incorrect Authorization, and has an estimated CVSS score of CVSS:3.1/AV:N/AC:H/PR:H/UI:N/S:C/C:L/I:N/A:N 3.0 Low. This issue wa...

CritBench: A Framework for Evaluating Cybersecurity Capabilities of Large Language Models in IEC 61850 Digital Substation Environments

The advancement of Large Language Models LLMs has raised concerns regarding their dual-use potential in cybersecurity. Existing evaluation frameworks overwhelmingly focus on Information Technology IT environments, failing to capture the constraints, and specialized protocols of Operational...

Spring AI Agentic Patterns (Part 6): AutoMemoryTools — Persistent Agent Memory Across Sessions

File-Based Long-Term Memory for Spring AI Agents Agents are only as useful as what they remember. Spring AI's Chat Memory stores the full conversation and can persist it across restarts, but when the window fills, the oldest messages are evicted. The upcoming Session API will add recursive...

PT-2026-30874

Name of the Vulnerable Software and Affected Versions runZero Platform versions prior to 4.0.260203.0 Description A flaw allowed MCP agents to access certificate information beyond their authorized organizational boundaries. This is categorized as CWE-863: Incorrect Authorization. Recommendations...

ClawLess: A Security Model of AI Agents

Autonomous AI agents powered by Large Language Models can reason, plan, and execute complex tasks, but their ability to autonomously retrieve information and run code introduces significant security risks. Existing approaches attempt to regulate agent behavior through training or prompting, which...

WebSP-Eval: Evaluating Web Agents on Website Security and Privacy Tasks

Web agents automate browser tasks, ranging from simple form completion to complex workflows like ordering groceries. While current benchmarks evaluate general-purpose performancee.g., WebArena or safety against malicious actionse.g., SafeArena, no existing framework assesses an agent's ability to...