CVE-2026-4515

A vulnerability has been found in Foundation Agents MetaGPT up to 0.8.1. This affects the function codegenerate of the file metagpt/ext/aflow/scripts/operator.py. The manipulation leads to code injection. It is possible to initiate the attack remotely. The exploit has been disclosed to the public...

CVE-2026-4515

Foundation Agents MetaGPT up to 0.8.1 contains a code injection vulnerability in metagpt/ext/aflow/scripts/operator.py: function code_generate. The issue allows remote initiation and is associated with a PROOF-OF-CONCEPT exploit; exploitation status is indicated by the sources as disclosed public...

CVE-2026-32051

OpenClaw versions prior to 2026.3.1 contain an authorization mismatch vulnerability that allows authenticated callers with operator.write scope to invoke owner-only tool surfaces including gateway and cron through agent runs in scoped-token deployments. Attackers with write-scope access can perfo...

PT-2026-26888

A vulnerability has been found in Foundation Agents MetaGPT up to 0.8.1. This affects the function code generate of the file metagpt/ext/aflow/scripts/operator.py. The manipulation leads to code injection. It is possible to initiate the attack remotely. The exploit has been disclosed to the publi...

CVE-2026-4515: Improper Control of Generation of Code

A vulnerability has been found in Foundation Agents MetaGPT up to 0.8.1. This affects the function codegenerate of the file metagpt/ext/aflow/scripts/operator.py. The manipulation leads to code injection. It is possible to initiate the attack remotely. The exploit has been disclosed to the public...

CVE-2026-4516: Improper Neutralization of Special Elements in Output Used by a Downstream Component

A vulnerability was found in Foundation Agents MetaGPT up to 0.8.1. This vulnerability affects unknown code of the file metagpt/actions/di/writeanalysiscode.py of the component DataInterpreter. The manipulation results in injection. It is possible to launch the attack remotely. The exploit has be...

T-MAP: Red-Teaming LLM Agents with Trajectory-Aware Evolutionary Search

While prior red-teaming efforts have focused on eliciting harmful text outputs from large language models LLMs, such approaches fail to capture agent-specific vulnerabilities that emerge through multi-step tool execution, particularly in rapidly growing ecosystems such as the Model Context Protoc...

Secure agentic AI end-to-end

Next week, RSAC™ Conference celebrates its 35-year anniversary as a forum that brings the security community together to address new challenges and embrace opportunities in our quest to make the world a safer place for all. As we look towards that milestone, agentic AI is reshaping industries...

Secure agentic AI end-to-end

Next week, RSAC™ Conference celebrates its 35-year anniversary as a forum that brings the security community together to address new challenges and embrace opportunities in our quest to make the world a safer place for all. As we look towards that milestone, agentic AI is reshaping industries...

Pensar Apex AI-Powered Penetration Testing

Pensar Apex is an AI-powered penetration testing using autonomous agents - directly in your terminal. Run blackbox and whitebox pentests that explore, reason, and surface real vulnerabilities...

CVE-2026-32013

OpenClaw is affected: versions prior to 2026.2.25 contain a symlink traversal in agents.files.get and agents.files.set that can read/write files outside the agent workspace. Attackers can access arbitrary host files within gateway process permissions by following symlinked allowlisted files, whic...

CVE-2026-32013 OpenClaw < 2026.2.25 - Symlink Traversal in agents.files Methods

OpenClaw versions prior to 2026.2.25 contain a symlink traversal vulnerability in the agents.files.get and agents.files.set methods that allows reading and writing files outside the agent workspace. Attackers can exploit symlinked allowlisted files to access arbitrary host files within gateway...

EUVD-2026-13275

OpenClaw versions prior to 2026.2.25 contain a symlink traversal vulnerability in the agents.files.get and agents.files.set methods that allows reading and writing files outside the agent workspace. Attackers can exploit symlinked allowlisted files to access arbitrary host files within gateway...

CVE-2026-32013 OpenClaw < 2026.2.25 - Symlink Traversal in agents.files Methods

OpenClaw versions prior to 2026.2.25 contain a symlink traversal vulnerability in the agents.files.get and agents.files.set methods that allows reading and writing files outside the agent workspace. Attackers can exploit symlinked allowlisted files to access arbitrary host files within gateway...

The Top 10 Threats Related to Agent Skills

Read about the top 10 critical threats related to Agent Skills that security teams should consider while building and evaluating agents...

aiops-ml (>=1.0.0, <=1.0.1), architxt (>=0.3.1, <=0.5.2) +64 more potentially affected by CVE-2025-15031 via mlflow-skinny (>=3.0.0rc0, <=3.8.1)

mlflow-skinny PYPI version =3.0.0rc0, =1.0.0, =0.3.1, =1.1.0b1, =0.0.1, =1.0.0b1, =1.0.0b1, =1.0.17.1, =1.23.0, =0.1.0, =0.1.0, =0.1.0, =0.0.1rc1, =2.5.0, =0.2.1, =0.7.0 and more Source cves: CVE-2025-15031 Source advisory: SNYK:PYTHON-MLFLOWSKINNY-16698159...

A Framework for Formalizing LLM Agent Security

Security in LLM agents is inherently contextual. For example, the same action taken by an agent may represent legitimate behavior or a security violation depending on whose instruction led to the action, what objective is being pursued, and whether the action serves that objective. However,...

Juju 安全漏洞

Juju is a canonical Juju open-source application orchestration engine. Versions of Juju from 3.1.6 to 3.6.18 have security vulnerabilities. These vulnerabilities stem from an authorization bypass in the Vault key backend implementation, which may allow authenticated unit agents to execute...

Orchid Security Recognized by Gartner® as a Representative Vendor of Guardian Agents

New York, United States, 17th March 2026, CyberNewswire...

Google Chrome Agents Resource Management Error Vulnerability

Google Chrome is a free web browser developed by Google Inc. A security vulnerability exists in Google Chrome Agents, which originates from re-referencing or using freed memory and can be exploited by remote attackers to execute arbitrary code...