golang.org/x/crypto/ssh/agent: SSH Agent servers: Denial of Service due to malformed messages

A flaw was found in the SSH Agent servers component golang.org/x/crypto/ssh/agent. This vulnerability allows a remote attacker to cause a denial of service DoS by sending a specially crafted, malformed message during new identity requests. The server fails to validate the size of these messages,...

CVE-2026-33817 vulnerabilities

Vulnerabilities for packages: vault-fips, grafana-fips, mattermost, commercial-grafana, consul-fips, elastic-agent-fips, datadog-agent, cloudbeat-fips, consul, commercial-expanso-edge, frankenphp-8.5, rke2-runtime, frankenphp-8.4, rke2-runtime-fips, grafana, kine, zot, loki, mattermost-fips,...

GHSA-6JWV-W5XF-7J27 vulnerabilities

Vulnerabilities for packages: vault-fips, grafana-fips, mattermost, commercial-grafana, consul-fips, elastic-agent-fips, datadog-agent, cloudbeat-fips, consul, commercial-expanso-edge, frankenphp-8.5, rke2-runtime, frankenphp-8.4, rke2-runtime-fips, grafana, kine, zot, loki, mattermost-fips,...

CLEANSTART-2026-FZ55932 SSH clients receiving SSH_AGENT_SUCCESS when expecting a typed response will panic and cause early termination of the client process

Multiple security vulnerabilities affect the istio-fips package. SSH clients receiving SSHAGENTSUCCESS when expecting a typed response will panic and cause early termination of the client process. See references for individual vulnerability details...

ACIArena: Toward Unified Evaluation for Agent Cascading Injection

Collaboration and information sharing empower Multi-Agent Systems MAS but also introduce a critical security risk known as Agent Cascading Injection ACI. In such attacks, a compromised agent exploits inter-agent trust to propagate malicious instructions, causing cascading failures across the...

Your Agent Is Mine: Measuring Malicious Intermediary Attacks on the LLM Supply Chain

Large language model LLM agents increasingly rely on third-party API routers to dispatch tool-calling requests across multiple upstream providers. These routers operate as application-layer proxies with full plaintext access to every in-flight JSON payload, yet no provider enforces cryptographic...

OpenClaw 安全漏洞

OpenClaw is an open-source intelligent artificial assistant developed by OpenClaw. Versions of OpenClaw prior to 2026.3.25 contained security vulnerabilities. These vulnerabilities stemmed from the gateway plugin’s sub-agent’s deleteSession function using a synthesized operator.admin runtime scop...

PT-2026-31790

Name of the Vulnerable Software and Affected Versions PraisonAI versions prior to 4.5.128 Description PraisonAI is a multi-agent teams system. The AgentOS deployment platform exposes a GET /api/agents endpoint that returns agent names, roles, and the first 100 characters of agent system...

openSUSE Security Advisory (SUSE-SU-2026:1194-1)

The remote host is missing an update for the SPDX-FileCopyrightText: 2026 Greenbone AG Some text descriptions might be excerpted from a referenced sources, and are Copyright C by the respective right holders. SPDX-License-Identifier: GPL-2.0-only ifdescription...

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...

PraisonAI Vulnerable to OS Command Injection

The executecommand function and workflow shell execution are exposed to user-controlled input via agent workflows, YAML definitions, and LLM-generated tool calls, allowing attackers to inject arbitrary shell commands through shell metacharacters. --- Description PraisonAI's workflow system and...

CVE-2026-39890

PraisonAI is a multi-agent teams system. Prior to 4.5.115, the AgentService.loadAgentFromFile method uses the js-yaml library to parse YAML files without disabling dangerous tags such as !!js/function and !!js/undefined. This allows an attacker to craft a malicious YAML file that, when parsed,...

CVE-2026-39889

PraisonAI is a multi-agent teams system. Prior to 4.5.115, the A2U Agent-to-User event stream server in PraisonAI exposes all agent activity without authentication. The createa2uroutes function registers the following endpoints with NO authentication checks: /a2u/info, /a2u/subscribe,...

CVE-2026-39891

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...

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...

CVE-2026-39890 PraisonAI Affected by Remote Code Execution via YAML Deserialization in Agent Definition Loading

PraisonAI is a multi-agent teams system. Prior to 4.5.115, the AgentService.loadAgentFromFile method uses the js-yaml library to parse YAML files without disabling dangerous tags such as !!js/function and !!js/undefined. This allows an attacker to craft a malicious YAML file that, when parsed,...

CVE-2026-39890

Prais onAI’s AgentService.loadAgentFromFile parses YAML with js-yaml without disabling dangerous tags (e.g., !!js/function, !!js/undefined), enabling attacker to upload a malicious agent definition and achieve remote code execution on the server. Affected software: PraisonAI (before 4.5.115). Roo...