CVE-2026-62209

OpenClaw versions 2026.5.10-beta.1 before 2026.6.5 contain an authorization bypass in the ClickClack agent-mode dispatch feature, which could ignore the toolsAllow policy check. When the affected feature is enabled and reachable, a lower-trust caller or configured input path could perform actions...

EUVD-2026-45097

OpenClaw versions 2026.5.10-beta.1 before 2026.6.5 contain an authorization bypass in the ClickClack agent-mode dispatch feature, which could ignore the toolsAllow policy check. When the affected feature is enabled and reachable, a lower-trust caller or configured input path could perform actions...

CVE-2026-62209

OpenClaw 2026.5.10-beta.1 before 2026.6.5 contains an authorization bypass in the ClickClack agent-mode dispatch feature. When enabled and reachable, a lower-trust caller or configured input path could bypass the required policy checks (toolsAllow), allowing actions that should require stronger a...

CVE-2026-62209 OpenClaw 2026.5.10-beta.1 < 2026.6.5 Authorization Bypass via agent-mode dispatch

OpenClaw versions 2026.5.10-beta.1 before 2026.6.5 contain an authorization bypass in the ClickClack agent-mode dispatch feature, which could ignore the toolsAllow policy check. When the affected feature is enabled and reachable, a lower-trust caller or configured input path could perform actions...

CVE-2026-62209 OpenClaw 2026.5.10-beta.1 < 2026.6.5 Authorization Bypass via agent-mode dispatch

OpenClaw versions 2026.5.10-beta.1 before 2026.6.5 contain an authorization bypass in the ClickClack agent-mode dispatch feature, which could ignore the toolsAllow policy check. When the affected feature is enabled and reachable, a lower-trust caller or configured input path could perform actions...

CVE-2026-6129

A vulnerability was detected in zhayujie chatgpt-on-wechat CowAgent up to 2.0.4. This affects an unknown function of the component Agent Mode Service. Performing a manipulation results in missing authentication. The attack can be initiated remotely. The exploit is now public and may be used. The...

EUVD-2026-21744

A vulnerability was detected in zhayujie chatgpt-on-wechat CowAgent up to 2.0.4. This affects an unknown function of the component Agent Mode Service. Performing a manipulation results in missing authentication. The attack can be initiated remotely. The exploit is now public and may be used. The...

CVE-2026-6129

The CVE-2026-6129 entry concerns zhayujie chatgpt-on-wechat CowAgent up to version 2.0.4. The vulnerability affects the Agent Mode Service component, with root cause described as a manipulation that results in missing authentication. Attack requires no privileges and can be initiated remotely ove...

CVE-2026-6129 zhayujie chatgpt-on-wechat CowAgent Agent Mode Service missing authentication

A vulnerability was detected in zhayujie chatgpt-on-wechat CowAgent up to 2.0.4. This affects an unknown function of the component Agent Mode Service. Performing a manipulation results in missing authentication. The attack can be initiated remotely. The exploit is now public and may be used. The...

CVE-2026-6129 zhayujie chatgpt-on-wechat CowAgent Agent Mode Service missing authentication

A vulnerability was detected in zhayujie chatgpt-on-wechat CowAgent up to 2.0.4. This affects an unknown function of the component Agent Mode Service. Performing a manipulation results in missing authentication. The attack can be initiated remotely. The exploit is now public and may be used. The...

CVE-2026-6129 zhayujie chatgpt-on-wechat CowAgent Agent Mode Service missing authentication

A vulnerability was detected in zhayujie chatgpt-on-wechat CowAgent up to 2.0.4. This affects an unknown function of the component Agent Mode Service. Performing a manipulation results in missing authentication. The attack can be initiated remotely. The exploit is now public and may be used. The...

CowAgent 访问控制错误漏洞

CowAgent is an intelligent assistant and scalable agent framework developed by zhayujie’s individual developer. Versions of CowAgent 2.0.4 and earlier contained a security vulnerability related to access control. This vulnerability stemmed from the absence of authentication in the Agent Mode...

GHSA-M855-R557-5RC5 Dozzle Agent Label-Based Access Control Bypass Allows Unauthorized Container Shell Access

Summary A flaw in Dozzle’s agent-backed shell endpoints allows a user restricted by label filters for example, label=env=dev to obtain an interactive root shell in out‑of‑scope containers for example, env=prod on the same agent host by directly targeting their container IDs. Note: Tested on v9.0....

Dozzle Agent Label-Based Access Control Bypass Allows Unauthorized Container Shell Access

Summary A flaw in Dozzle’s agent-backed shell endpoints allows a user restricted by label filters for example, label=env=dev to obtain an interactive root shell in out‑of‑scope containers for example, env=prod on the same agent host by directly targeting their container IDs. Note: Tested on v9.0....

EUVD-2017-16825

Malware in sbrugna...

EUVD-2017-16237

Malware in sbrugna...

EUVD-2017-16824

Malware in sbrugna...

Safeguarding VS Code against prompt injections

The Copilot Chat extension for VS Code has been evolving rapidly over the past few months, adding a wide range of new features. Its new agent mode lets you use multiple large language models LLMs, built-in tools, and MCP servers to write code, make commit requests, and integrate with external...

VulnCheck KEV: CVE-2017-7199

Nessus 6.6.2 - 6.10.3 contains a flaw related to insecure permissions that may allow a local attacker to escalate privileges when the software is running in Agent Mode. Version 6.10.4 fixes this issue...

Stowaway - Multi-hop Proxy Tool For Pentesters

Stowaway is Multi-hop proxy tool for security researchers and pentesters Users can easily proxy their network traffic to intranet nodes multi-layer PS: The files under demo folder are Stowaway's beta version,it's still functional, you can check the detail by README.md file under the demo folder...