20084 matches found
CVE-2026-32048 OpenClaw < 2026.3.1 - Sandbox Escape via Cross-Agent sessions_spawn
OpenClaw versions prior to 2026.3.1 fail to enforce sandbox inheritance during cross-agent sessionsspawn operations, allowing sandboxed sessions to create child processes under unsandboxed agents. An attacker with a sandboxed session can exploit this to spawn child runtimes with sandbox.mode set ...
CVE-2026-32048
CVE-2026-32048 affects OpenClaw before 2026.3.1. The root cause is failure to enforce sandbox inheritance during cross-agent sessions_spawn, enabling a sandboxed session to create child processes under unsandboxed agents and spawn runtimes with sandbox.mode set to off, bypassing runtime confineme...
PT-2026-26730
OpenClaw versions prior to 2026.3.1 fail to enforce sandbox inheritance during cross-agent sessions spawn operations, allowing sandboxed sessions to create child processes under unsandboxed agents. An attacker with a sandboxed session can exploit this to spawn child runtimes with sandbox.mode set...
AEGIS: From Clues to Verdicts -- Graph-Guided Deep Vulnerability Reasoning Via Dialectics and Meta-Auditing
Large Language Models LLMs are increasingly adopted for vulnerability detection, yet their reasoning remains fundamentally unsound. We identify a root cause shared by both major mitigation paradigms agent-based debate and retrieval augmentation: reasoning in an ungrounded deliberative space that...
PT-2026-26733
Name of the Vulnerable Software and Affected Versions OpenClaw versions prior to 2026.3.1 Description An authorization mismatch exists that allows authenticated callers with operator.write scope to invoke owner-only tool surfaces, including gateway and cron, through agent runs in scoped-token...
MAL-2026-2006 Malicious code in mangrove-sdk (PyPI)
--- -= Per source details. Do not edit below this line.=- Source: kam193 d6714958f20775c2347e9c8b606d1de2e28ed29fe4b1a82261ca4fb966fc20fa During installation, package attempts to modify LLM configuration files to provide a backdoor instruction for further control over an AI agent. --- Category:...
MAL-2026-2004 Malicious code in flyio-token-client-efgh (PyPI)
--- -= Per source details. Do not edit below this line.=- Source: kam193 2b09830263d8a35450ca657294a1725c441f2f7fe49cc7946e261e8f18401464 During installation, package attempts to modify LLM configuration files to provide a backdoor instruction for further control over an AI agent. --- Category:...
EUVD-2026-13766
mcp-memory-service is an open-source memory backend for multi-agent systems. Prior to version 10.25.1, when the HTTP server is enabled MCPHTTPENABLED=true, the application configures FastAPI's CORSMiddleware with alloworigins='', allowcredentials=True, allowmethods="", and allowheaders="". The...
Secure agentic AI end-to-end
Next week, RSAC™ Conference celebrates its 35-year anniversary as a forum that brings the security community together to address new challenges and embrace opportunities in our quest to make the world a safer place for all. As we look towards that milestone, agentic AI is reshaping industries...
CVE-2026-32946
Harden-Runner (GitHub Actions security agent) contains a vulnerability in versions 2.15.1 and earlier that allows bypassing egress-policy: block network restrictions by using DNS queries over TCP. The underlying issue is that DNS over TCP is not adequately restricted when the allowed-endpoints li...
GHSA-479M-364C-43VC vulnerabilities
Vulnerabilities for packages: mattermost, rancher, dex, rancher-agent, teleport...
Langflow 安全漏洞
Langflow is an open-source visualization framework developed by Langflow for building multi-agent and RAG applications. Versions of Langflow prior to 1.9.0 contained a security vulnerability. This vulnerability stemmed from the deleteapikeyroute endpoint, which did not verify the ownership of the...
Memory Poisoning and Secure Multi-Agent Systems
Memory poisoning attacks for Agentic AI and multi-agent systems MAS have recently caught attention. It is partially due to the fact that Large Language Models LLMs facilitate the construction and deployment of agents. Different memory systems are being used nowadays in this context, including...
An Agentic Multi-Agent Architecture for Cybersecurity Risk Management
Getting a real cybersecurity risk assessment for a small organization is expensive -- a NIST CSF-aligned engagement runs $15,000 on the low end, takes weeks, and depends on practitioners who are genuinely scarce. Most small companies skip it entirely. We built a six-agent AI system where each age...
ROS-20260320-73-0007
A vulnerability in the ssh-agent library ssh-agent server for the Go crypto programming language involves reading beyond buffer boundaries in memory. Exploitation of the vulnerability could allow an attacker acting remotely to cause a denial of service...
CVE-2026-32001
OpenClaw versions prior to 2026.2.22 contain an authentication bypass vulnerability that allows clients authenticated with a shared gateway token to connect as role=node without device identity verification. Attackers can exploit this by claiming the node role during WebSocket handshake to inject...
CVE-2026-32035
OpenClaw CVE-2026-32035 affects openclaw prior to 2026.3.2. The Discord voice transcript path in agentCommand omits senderIsOwner, causing the flag to default to true and enabling non-owner participants in mixed-trust channels to access owner-only tools (gateway, cron). Affected versions: ≤ 2026....
CVE-2026-32013 OpenClaw < 2026.2.25 - Symlink Traversal in agents.files Methods
OpenClaw versions prior to 2026.2.25 contain a symlink traversal vulnerability in the agents.files.get and agents.files.set methods that allows reading and writing files outside the agent workspace. Attackers can exploit symlinked allowlisted files to access arbitrary host files within gateway...
golang.org/x/crypto/ssh/agent: golang.org/x/crypto/ssh/agent: SSH client panic due to unexpected SSH_AGENT_SUCCESS
A flaw in golang.org/x/crypto/ssh/agent causes the SSH agent client to panic when a peer responds with the generic SSHAGENTSUCCESS 0x06 message to requests expecting typed replies e.g., List, Sign. The unmarshal layer produces an unexpected message type, which the client code does not handle,...