CVE-2026-107292

Pydantic AI is a Python agent framework for building applications and workflows with Generative AI. From 1.34.0 until 2.30.0, the Agent.toweb and clai web development chat server does not validate the Host header, allowing a website visited by a developer to use DNS rebinding to reach a...

GO-2026-6657 SiYuan Agent Tools SSRF via DNS-Rebinding TOCTOU (Bypass of CheckHostSSRF) in github.com/siyuan-note/siyuan/kernel

SiYuan Agent Tools SSRF via DNS-Rebinding TOCTOU Bypass of CheckHostSSRF in github.com/siyuan-note/siyuan/kernel...

ai.hyacinth.framework:core-service-bus-support (>=0.5.0, <=0.5.24), ai.platon.pulsar:browser4-agent-tools (>=4.13.5, <=4.14.0-rc.2) +3403 more potentially affected by CVE-2026-106121 via com.rabbitmq:amqp-client (>=5.0.0, <=5.36.0)

com.rabbitmq:amqp-client MAVEN version =5.0.0, =0.5.0, =4.13.5, =4.13.5, =4.13.5, =4.13.5, =4.13.5, =4.13.5, =4.13.5, =4.13.5, =4.13.5, =4.13.5, =4.13.5, =4.13.5, =4.14.0-rc.2 - ai.platon.pulsar:browser4-seo 4.14.0-rc.2 and more Source cves: CVE-2026-106121 Source advisory: MEND:CVE-2026-106121...

CVE-2026-51870

DeepTutor v1.4.0 is vulnerable to command execution in /tutorbot/agent/tools/shell.py:ExecTool.execute...

CVE-2026-51870

DeepTutor v1.4.0 is vulnerable to command execution in /tutorbot/agent/tools/shell.py:ExecTool.execute...

PT-2026-103618

Name of the Vulnerable Software and Affected Versions DeepTutor version 1.4.0 Description An OS command injection issue exists in the execute function within the /tutorbot/agent/tools/shell.py:ExecTool component, allowing for remote command execution. Recommendations At the moment, there is no...

EUVD-2026-78394

PraisonAI is a multi-agent teams system. From 1.6.0 until 1.7.2, AgentOS in src/praisonai-ts/src/os/agentos.ts uses the 0.0.0.0 default from src/praisonai-ts/src/os/config.ts and registers GET /api/agents and POST /api/chat without authentication middleware. A remote caller who can reach the...

CVE-2026-90809: Improper Neutralization of Argument Delimiters in a Command

A vulnerability was identified in HKUDS nanobot up to 0.2.1. The affected element is the function ExecTool.guardcommand/ExecTool.spawn of the file nanobot/agent/tools/shell.py of the component ExecTool. Such manipulation leads to argument injection. It is possible to launch the attack remotely. T...

CVE-2026-90808: Incomplete List of Disallowed Inputs

A vulnerability was determined in HKUDS nanobot up to 0.2.1. Impacted is the function ExecTool.guardcommand/ExecTool.spawn of the file nanobot/agent/tools/shell.py of the component ExecTool. This manipulation causes incomplete blacklist. It is possible to initiate the attack remotely. Patch name:...

PYSEC-2026-3888 PraisonAI: [Path Traversal] agent tools escape the configured workspace via symlinks

Summary PraisonAI's praisonai.code tool wrappers exported as CODETOOLS for agents expose a workspace setting that the module itself treats as a path-traversal security boundary — readfile, writefile, applydiff, and searchreplace explicitly call ispathwithindirectory and return "… is outside the...

CVE-2026-84427: Improper Resource Shutdown or Release

A vulnerability was determined in zhayujie CowAgent up to 2.1.7. Affected is an unknown function of the file agent/tools/bash/bash.py of the component Bash Tool. Executing a manipulation can lead to denial of service. The attack can be launched remotely. The exploit has been publicly disclosed an...

CVE-2026-82234 SiYuan before v3.8.1 SSRF via DNS-Rebinding TOCTOU

SiYuan versions before v3.8.1 contain a server-side request forgery vulnerability in the httprequest and webfetch agent tools that perform DNS resolution only at guard time without validating the connect-time resolution. Attackers can use DNS rebinding to answer the guard resolution with a public...

CVE-2026-55540 PraisonAI: [Path Traversal] agent tools escape the configured workspace via symlinks

PraisonAI is a multi-agent teams system. Prior to praisonai 4.6.51, ispathwithindirectory uses os.path.abspath rather than os.path.realpath for the workspace boundary. A symlink inside workspace can point outside and still pass the check, allowing readfile and other code tools to access files...

CVE-2026-75911

CodeWhale versions before 0.8.64 fail to properly validate the allowshell configuration parameter from project config files, allowing attackers to enable arbitrary shell command execution by committing a malicious .codewhale/config.toml file to a repository. When a user clones and opens the...

PT-2026-69148

Name of the Vulnerable Software and Affected Versions HKUDS nanobot versions prior to 0.3.0 Description A flaw in the Login-shell Environment Handler allows local attackers to cause information disclosure. The issue exists in the ExecTool. prepare command function within the...

PT-2026-69139

Name of the Vulnerable Software and Affected Versions HKUDS nanobot versions prior to 0.3.0 Description Improper access controls exist within the MCP enabledTools Scope Handler component. The issue resides in the connect mcp servers function located in the nanobot/agent/tools/mcp.py file. This fl...

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...

Linux Distros Unpatched Vulnerability : CVE-2026-65698

The Linux/Unix host has one or more packages installed that are impacted by a vulnerability without a vendor supplied patch available. - 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 file...

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://...

CVE-2026-65698

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://...