CVE-2026-5970 FoundationAgents MetaGPT HumanEvalBenchmark/MBPPBenchmark check_solution code injection

A vulnerability was detected in FoundationAgents MetaGPT up to 0.8.1. This affects the function checksolution of the component HumanEvalBenchmark/MBPPBenchmark. Performing a manipulation results in code injection. The attack may be initiated remotely. The exploit is now public and may be used. Th...

cybersentinel-agent

CyberSentinel Agent Defensive cybersecurity agent framework w...

PT-2026-31791

Name of the Vulnerable Software and Affected Versions PraisonAIAgents versions prior to 1.5.128 Description PraisonAIAgents is a multi-agent teams system. The list files tool in FileTools validates the directory parameter against workspace boundaries using the validate path function, but passes t...

PT-2026-31786

Name of the Vulnerable Software and Affected Versions PraisonAIAgents versions prior to 1.5.128 Description PraisonAIAgents is a multi-agent teams system. The read skill file function in skill tools.py allows reading arbitrary files from the filesystem due to an unrestricted skill path parameter...

PT-2026-31679

Name of the Vulnerable Software and Affected Versions FoundationAgents MetaGPT versions prior to 0.8.2 Description A flaw in the XML Handler component allows remote attackers to cause improper neutralization of directives in dynamically evaluated code. This issue occurs within the ActionNode.xml...

PT-2026-31669

Name of the Vulnerable Software and Affected Versions FoundationAgents MetaGPT versions up to 0.8.1 Description A flaw exists in the check solution function within the HumanEvalBenchmark/MBPPBenchmark component of FoundationAgents MetaGPT. Manipulation of this function can lead to code injection,...

PT-2026-31767

Name of the Vulnerable Software and Affected Versions OpenClaw versions through 2026.2.22 Description OpenClaw through version 2026.2.22 has a symlink traversal issue in the agents.create and agents.update handlers. These handlers use fs.appendFile on IDENTITY.md without proper symlink containmen...

OpenClaw 安全漏洞

OpenClaw is an open-source intelligent artificial assistant developed by OpenClaw. Versions of OpenClaw prior to 2026.2.22 contained security vulnerabilities. These vulnerabilities were caused by symbolic link traversal issues in the agents.create and agents.update handlers, which could lead to...

CVE-2026-39888

PraisonAI’s PraisonAIAgents contain a sandbox escape in execute_code() (subprocess mode) prior to version 1.5.115. The subprocess wrapper blocks only a subset of attributes, and the missing frame-traversal attributes (traceback , tb_frame, f_back, f_builtins) can be chained via a caught exception...

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...

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...

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...

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...

asimov-agents (>=0.0.3 <=0.1.2), dcspy (>=3.6.2 <=3.8.1) +1 more potentially affected by CVE-2026-34444 via lupa (>=2.2.0 <=2.6.0)

lupa PYPI version =2.2.0, =0.0.3, =3.6.2, =3.8.1 - draw-palette =0.3.0 Source cves: CVE-2026-34444 Source advisory: SNYK:PYTHON-LUPA-15954200...

asimov-agents (>=0.0.3 <=0.1.2), corva-sdk (>=1.4.0 <=1.12.1) +6 more potentially affected by CVE-2026-34444 via lupa (>=1.14.1 <=2.5.0)

lupa PYPI version =1.14.1, =0.0.3, =1.4.0, =3.6.2, =0.1.1, =1.6.0, =0.0.4, =0.0.1, =0.0.4 Source cves: CVE-2026-34444 Source advisory: OSV:GHSA-69V7-XPR6-6GJM...

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...

databricks-agents (>=0.1.0 <=1.0.0rc1), datamint (>=2.5.0 <=2.5.2) +18 more potentially affected by CVE-2026-33865 via mlflow (>=3.0.0rc2 <=3.10.1)

mlflow PYPI version =3.0.0rc2, =0.1.0, =2.5.0, =7.1.1, =0.2.0, =3.10.1, =1.0.1, =1.0.1, =3.0.15, =0.2.0.dev0, =0.6.7, =0.1.19, =0.1.0, =0.1.8 and more Source cves: CVE-2026-33865 Source advisory: SNYK:PYTHON-MLFLOW-15923609...

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) ...