EUVD-2026-77763

A security flaw has been discovered in cosmicstack-labs mercury-agent up to 1.1.13. The impacted element is the function PermissionManager.checkShellCommand of the file mercury-agent/src/capabilities/permissions.ts of the component Shell Command Permission Check. Performing a manipulation results...

CVE-2026-90810 cosmicstack-labs mercury-agent Shell Command Permission Check permissions.ts PermissionManager.checkShellCommand improper authorization

A security flaw has been discovered in cosmicstack-labs mercury-agent up to 1.1.13. The impacted element is the function PermissionManager.checkShellCommand of the file mercury-agent/src/capabilities/permissions.ts of the component Shell Command Permission Check. Performing a manipulation results...

CVE-2026-19543 Multiple vulnerabilities affect IBM License Key Server Administration and Reporting Tool and IBM LKS Administration Agent

IBM Common Licensing Agent 9.0, Agent 9.0.0.1, Agent 9.0.0.2, ART 9.0, ART 9.0.0.1, and ART 9.0.0.2 performs input validation exclusively on the client side and fails to enforce the same restrictions on the server side. An attacker can modify requests to bypass validation controls and submit...

EUVD-2026-77761

IBM Common Licensing Agent 9.0, Agent 9.0.0.1, Agent 9.0.0.2, ART 9.0, ART 9.0.0.1, and ART 9.0.0.2 performs input validation exclusively on the client side and fails to enforce the same restrictions on the server side. An attacker can modify requests to bypass validation controls and submit...

CVE-2026-19543

IBM Common Licensing Agent and IBM LKS Administration and Reporting Tool (ART) , versions 9.0, 9.0.0.1, and 9.0.0.2 , perform input validation exclusively on the client side without enforcing equivalent restrictions on the server side. An attacker with local access can modify requests to bypass v...

AI Agent Security Readiness: The Federal Standard You Should Get Ahead Of

Here's the uncomfortable part first: in August 2026, researchers found AI agents connected to Hugging Face running loose inside enterprise networks. No owner, no audit trail, nobody who could tell you they existed until something broke. If that sentence made your stomach drop a little, good,...

CVE-2026-90807 nanocoai NanoClaw Attachment agent-route.ts forwardAttachedFiles link following

A vulnerability was found in nanocoai NanoClaw up to 2.1.17. This issue affects the function forwardAttachedFiles of the file src/modules/agent-to-agent/agent-route.ts of the component Attachment Handler. The manipulation results in link following. The attack may be performed from remote. The...

CVE-2026-90807

CVE-2026-90807 is a link following vulnerability in nanocoai NanoClaw (up to version 2.1.17 ), located in the function forwardAttachedFiles within the file src/modules/agent-to-agent/agent-route.ts of the Attachment Handler component. A remote attacker with low privileges can exploit this without...

CVE-2026-90807 nanocoai NanoClaw Attachment agent-route.ts forwardAttachedFiles link following

A vulnerability was found in nanocoai NanoClaw up to 2.1.17. This issue affects the function forwardAttachedFiles of the file src/modules/agent-to-agent/agent-route.ts of the component Attachment Handler. The manipulation results in link following. The attack may be performed from remote. The...

porterminal v1.2.0

Give your agent any computer One command. One URL. A real terminal for your agent, a live view for you. Run Porterminal on a Windows, macOS, or Linux computer and give the generated link to your AI agent. It gets a real shell with the files, tools, and projects on that machine. Open the same link...

OESA-2026-3747 openssh security update

An open source implementation of SSH protocol version 2 Security Fixes: In ssh-agent in OpenSSH before 10.5, some operations can occur remotely but were intended to occur only locally, including operations that add tokens or use keys. This is caused by misinteraction between agent locking and the...

CVE-2026-57131

PraisonAI is a multi-agent teams system. Prior to 4.6.58, praisonai.jobs.server.createapp mounts praisonai.jobs.router.createrouter under /api/v1/runs without authentication or per-job authorization. Network clients can submit attacker-controlled prompts and agent configuration, list and read job...

CVE-2026-57132

PraisonAI is a multi-agent teams system. Prior to 4.6.62, setting PRAISONAICALLAUTH to disabled makes verifytoken accept requests to /api/v1/agents/id/invoke without CALLSERVERTOKEN authentication. Deployments that use the application's advertised opt-out can expose registered agents and their...

CVE-2026-57124

PraisonAI is a multi-agent teams system. Prior to 4.6.59, the default UI host applications expose POST /api/mcp/connect without mandatory authentication and accept caller-controlled command and args values that PraisonAIUI passes to StdioMCPClient to start a local process. Because the UI commands...

golang.org/x/crypto/ssh/agent: golang.org/x/crypto/ssh/agent: Security bypass due to improper handling of key restrictions

A flaw was found in golang.org/x/crypto/ssh/agent. When a key was added to a remote agent, security restrictions, known as constraint extensions, were not properly processed during the request. This allowed these restrictions to be silently removed when keys were forwarded, leading to the...

CVE-2026-57132 PraisonAI: PRAISONAI_CALL_AUTH=disabled environment variable unconditionally disables authentication

PraisonAI is a multi-agent teams system. Prior to 4.6.62, setting PRAISONAICALLAUTH to disabled makes verifytoken accept requests to /api/v1/agents/id/invoke without CALLSERVERTOKEN authentication. Deployments that use the application's advertised opt-out can expose registered agents and their...

CVE-2026-57132 PraisonAI: PRAISONAI_CALL_AUTH=disabled environment variable unconditionally disables authentication

PraisonAI is a multi-agent teams system. Prior to 4.6.62, setting PRAISONAICALLAUTH to disabled makes verifytoken accept requests to /api/v1/agents/id/invoke without CALLSERVERTOKEN authentication. Deployments that use the application's advertised opt-out can expose registered agents and their...

CVE-2026-57132

PraisonAI is an AI multi-agent framework. Prior to 4.6.62 , setting the PRAISONAI_CALL_AUTH=disabled environment variable causes the verify_token function (in agent_invoke.py) to return immediately, unconditionally bypassing all authentication on the /api/v1/agents/{id}/invoke endpoint. Because t...

EUVD-2026-77596

PraisonAI is a multi-agent teams system. Prior to 4.6.62, setting PRAISONAICALLAUTH to disabled makes verifytoken accept requests to /api/v1/agents/id/invoke without CALLSERVERTOKEN authentication. Deployments that use the application's advertised opt-out can expose registered agents and their...

CVE-2026-57132 PraisonAI: PRAISONAI_CALL_AUTH=disabled environment variable unconditionally disables authentication

PraisonAI is a multi-agent teams system. Prior to 4.6.62, setting PRAISONAICALLAUTH to disabled makes verifytoken accept requests to /api/v1/agents/id/invoke without CALLSERVERTOKEN authentication. Deployments that use the application's advertised opt-out can expose registered agents and their...