CVE-2026-29870

The CVE-2026-29870 entry describes a directory traversal in the agentic-context-engine (versions up to 0.7.1) that enables arbitrary file writes via the checkpoint_dir parameter in OfflineACE.run. The root cause is that save_to_file in ace/skillbook.py does not normalize or validate filesystem pa...

TrendAI™ Research at RSAC 2026: Advancing Defense Across AI‑Driven and Cyber‑Physical Threats

TrendAI™ Research explored agentic AI cybercrime and EV infrastructure security through two research sessions at RSAC 2026...

Addressing the OWASP Top 10 Risks in Agentic AI with Microsoft Copilot Studio

Agentic AI is moving fast from pilots to production. That shift changes the security conversation. These systems do not just generate content. They can retrieve sensitive data, invoke tools, and take action using real identities and permissions. When something goes wrong, the failure is not limit...

Addressing the OWASP Top 10 Risks in Agentic AI with Microsoft Copilot Studio

Agentic AI is moving fast from pilots to production. That shift changes the security conversation. These systems do not just generate content. They can retrieve sensitive data, invoke tools, and take action using real identities and permissions. When something goes wrong, the failure is not limit...

CVE-2026-33873

Langflow is a tool for building and deploying AI-powered agents and workflows. Prior to version 1.9.0, the Agentic Assistant feature in Langflow executes LLM-generated Python code during its validation phase. Although this phase appears intended to validate generated component code, the...

Arbitrary Code Injection

Overview Affected versions of this package are vulnerable to Arbitrary Code Injection through the Agentic Assistant validation process. An attacker can execute arbitrary server-side Python code by supplying input that causes the assistant to return malicious component code, which is then...

CVE-2026-33873

Langflow is a tool for building and deploying AI-powered agents and workflows. Prior to version 1.9.0, the Agentic Assistant feature in Langflow executes LLM-generated Python code during its validation phase. Although this phase appears intended to validate generated component code, the...

PYSEC-2026-82

Langflow is a tool for building and deploying AI-powered agents and workflows. Prior to version 1.9.0, the Agentic Assistant feature in Langflow executes LLM-generated Python code during its validation phase. Although this phase appears intended to validate generated component code, the...

PYSEC-2026-82

Langflow is a tool for building and deploying AI-powered agents and workflows. Prior to version 1.9.0, the Agentic Assistant feature in Langflow executes LLM-generated Python code during its validation phase. Although this phase appears intended to validate generated component code, the...

CVE-2026-33873

CVE-2026-33873 affects Langflow. Before v1.9.0, the Agentic Assistant feature can execute LLM-generated Python code during its validation phase, reaching dynamic execution sinks and instantiating the generated class server-side. In deployments where an attacker can access the Agentic Assistant an...

CVE-2026-33873 Langflow has Authenticated Code Execution in Agentic Assistant Validation

Langflow is a tool for building and deploying AI-powered agents and workflows. Prior to version 1.9.0, the Agentic Assistant feature in Langflow executes LLM-generated Python code during its validation phase. Although this phase appears intended to validate generated component code, the...

CVE-2026-33873 Langflow has Authenticated Code Execution in Agentic Assistant Validation

Langflow is a tool for building and deploying AI-powered agents and workflows. Prior to version 1.9.0, the Agentic Assistant feature in Langflow executes LLM-generated Python code during its validation phase. Although this phase appears intended to validate generated component code, the...

CVE-2026-33873

Langflow is a tool for building and deploying AI-powered agents and workflows. Prior to version 1.9.0, the Agentic Assistant feature in Langflow executes LLM-generated Python code during its validation phase. Although this phase appears intended to validate generated component code, the...

CVE-2026-33873 Langflow has Authenticated Code Execution in Agentic Assistant Validation

Langflow is a tool for building and deploying AI-powered agents and workflows. Prior to version 1.9.0, the Agentic Assistant feature in Langflow executes LLM-generated Python code during its validation phase. Although this phase appears intended to validate generated component code, the...

Langflow 代码注入漏洞

Langflow is an open-source visualization framework developed by Langflow for building multi-agent and RAG applications. Prior to Langflow 1.9.0, there was a code injection vulnerability. This vulnerability stemmed from the Agentic Assistant feature, which executed Python code generated by the LLM...

Clawed and Dangerous: Can We Trust Open Agentic Systems?

Open agentic systems combine LLM-based planning with external capabilities, persistent memory, and privileged execution. They are used in coding assistants, browser copilots, and enterprise automation. OpenClaw is a visible instance of this broader class. Without much attention yet, their securit...

GHSA-V8HW-MH8C-JXFC Langflow has Authenticated Code Execution in Agentic Assistant Validation

Description 1. Summary The Agentic Assistant feature in Langflow executes LLM-generated Python code during its validation phase. Although this phase appears intended to validate generated component code, the implementation reaches dynamic execution sinks and instantiates the generated class...

Langflow has Authenticated Code Execution in Agentic Assistant Validation

Description 1. Summary The Agentic Assistant feature in Langflow executes LLM-generated Python code during its validation phase. Although this phase appears intended to validate generated component code, the implementation reaches dynamic execution sinks and instantiates the generated class...

PT-2026-28544

Name of the Vulnerable Software and Affected Versions Langflow versions prior to 1.9.0 Description Langflow's Agentic Assistant feature, prior to version 1.9.0, executes LLM-generated Python code during validation. This implementation allows for arbitrary server-side Python execution if an attack...

Policy-Guided Threat Hunting: An LLM Enabled Framework with Splunk SOC Triage

With frequently evolving Advanced Persistent Threats APTs in cyberspace, traditional security solutions approaches have become inadequate for threat hunting for organizations. Moreover, SOC Security Operation Centers analysts are often overwhelmed and struggle to analyze the huge volume of logs...