CVE-2026-65698

A flaw was found in Void through 1.3.4 in the AI agent file-reading tools readfile, lsdir, getdirtree, and search. Those tools do not confine paths to the open workspace and can accept absolute paths or file:// URIs, including bypassing the approval gate. An attacker who can inject instructions...

CVE-2026-65698 Void 1.3.4 Path Traversal via AI Agent File-Reading Tools

Void through 1.3.4 contains a path traversal vulnerability in the AI agent file-reading tools that allows network-adjacent attackers to read arbitrary host files outside the open workspace by injecting instructions into content the agent processes. Attackers can supply absolute paths or file://...

EUVD-2026-48312

Void through 1.3.4 contains a path traversal vulnerability in the AI agent file-reading tools that allows network-adjacent attackers to read arbitrary host files outside the open workspace by injecting instructions into content the agent processes. Attackers can supply absolute paths or file://...

CVE-2026-15669

Technical details (affected products, vulnerable components, exploit vectors) are not publicly available in the provided documents. Monitor for updates.

PYSEC-2026-2917 PraisonAI has Template Injection in Agent Tool Definitions

Summary Direct insertion of unescaped user input into template-rendering tools allows arbitrary code execution via specially crafted agent instructions. Details The createagentcentrictools function returns tools like acpcreatefile that process file content using template rendering. When user inpu...

PT-2026-52168

Name of the Vulnerable Software and Affected Versions Drupal AI versions 0.0.0 through 1.2.17 Drupal AI versions 1.3.0 through 1.3.8 Drupal AI versions 1.4.0 through 1.4.3 Description A missing authorization issue allows forceful browsing. Certain Drupal core actions exposed as agent tools lack...

AI (Artificial Intelligence) - Moderately critical - Access bypass - SA-CONTRIB-2026-055

This module enables you to utilize an agent to use Drupal core actions tools with bypassed access. Certain Drupal core actions, exposed as agent tools did not have correct access validation, and some core actions were missing associated access-level definitions. This vulnerability is mitigated by...

Arbitrary Code Injection

Overview PraisonAI is a PraisonAI is an AI Agents Framework with Self Reflection. PraisonAI application combines PraisonAI Agents, AutoGen, and CrewAI into a low-code solution for building and managing multi-agent LLM systems, focusing on simplicity, customisation, and efficient human-agent...

CVE-2026-39891

PraisonAI’s multi-agent system contains a template injection in the create_agent_centric_tools() function prior to version 4.5.115. Tools such as acp_create_file process file content via template rendering, and user input from agent.start() could be rendered as template expressions instead of bei...

CVE-2026-39891 PraisonAI has a Template Injection in Agent Tool Definitions

PraisonAI is a multi-agent teams system. Prior to 4.5.115, the createagentcentrictools function returns tools like acpcreatefile that process file content using template rendering. When user input from agent.start is passed directly into these tools without escaping, template expressions in the...

CVE-2026-39891 PraisonAI has a Template Injection in Agent Tool Definitions

PraisonAI is a multi-agent teams system. Prior to 4.5.115, the createagentcentrictools function returns tools like acpcreatefile that process file content using template rendering. When user input from agent.start is passed directly into these tools without escaping, template expressions in the...

GHSA-HWG5-X759-7WJG PraisonAI has Template Injection in Agent Tool Definitions

Summary Direct insertion of unescaped user input into template-rendering tools allows arbitrary code execution via specially crafted agent instructions. Details The createagentcentrictools function returns tools like acpcreatefile that process file content using template rendering. When user inpu...

CVE-2026-27967

Zed, a code editor, has a symlink escape vulnerability in versions prior to 0.225.9 in Agent file tools readfile, editfile. It allows reading and writing files outside the project directory when a project contains symbolic links pointing to external paths. This bypasses the intended workspace...

CVE-2026-27967

Zed, a code editor, has a symlink escape vulnerability in versions prior to 0.225.9 in Agent file tools readfile, editfile. It allows reading and writing files outside the project directory when a project contains symbolic links pointing to external paths. This bypasses the intended workspace...

Juju-run Agent Privilege Escalation

This module attempts to gain root privileges on Juju agent systems running the juju-run agent utility. Juju agent systems running agent tools prior to version 1.25.12, 2.0.x before 2.0.4, and 2.1.x before 2.1.3, provide a UNIX domain socket to manage software "units" without setting appropriate...

Empire: a PowerShell post-exploitation Agent tools-vulnerability warning-the black bar safety net

Empire is a purely PowerShell post-exploitation Agent tools, it is built on cryptography, secure communications and flexible architecture. Empire realize the need to powershell. exe you can run a PowerShell proxy function. Rapid deployment post-exploit module, from the keyboard recorder to...