CVE-2026-82233 SiYuan before v3.8.1 Path Traversal via asset.upload

SiYuan before v3.8.1 contains a path traversal vulnerability in the asset.upload MCP tool that accepts arbitrary absolute file paths without workspace boundary validation. Attackers can induce the AI Agent to upload sensitive files such as SSH keys or credentials from outside the workspace into t...

CVE-2026-82233 SiYuan before v3.8.1 Path Traversal via asset.upload

SiYuan before v3.8.1 contains a path traversal vulnerability in the asset.upload MCP tool that accepts arbitrary absolute file paths without workspace boundary validation. Attackers can induce the AI Agent to upload sensitive files such as SSH keys or credentials from outside the workspace into t...

OpenAI Says Reward Hacking Drove AI Agents to Exploit Zero-Days and Breach Hugging Face

OpenAI on Wednesday revealed that reward hacking was a key driver behind the artificial intelligence AI-powered hack of Hugging Face last month, adding that it found evidence of misaligned behavior as early as late May. The incident, the company said, took place during cybersecurity evaluations o...

OpenClaw went viral. Meet the maintainers building and securing it.

What began as a personal experiment quickly became a global open source project with extraordinary momentum. OpenClaw is a personal AI assistant that runs on users' devices and connects with the messaging channels they already use. Started by Peter Steinberger as a weekend project in November 202...

When an AI Agent Turned Attacker: What Qualys Sees Across Every Phase of the Hugging Face Kubernetes Intrusion

A phase-by-phase detection mapping of the first publicly documented autonomous agent intrusion against production infrastructure — including the phases where no product in our category sees anything at all. Executive Summary On July 9, 2026, an autonomous AI agent running inside an OpenAI...

hermetic

Der agentenisolierte Credential-Broker. Ihr KI-Agent führt den authentifizierten Aufruf durch. Er sieht nie den Schlüssel. -brightgreen?style=flat-square Webseite · Installation · Schnellstart · Funktionsweise · Sicherheitsmodell · Schwachstelle melden !IMPORTANT Ihr KI-Agent arbeitet auf der ★★★...

CVE-2026-62674 Omnigent: Shared Agent Bundle Overwrite Leads to Authenticated Runner RCE

Omnigent is an open-source AI agent framework and meta-harness for orchestrating coding agents. Prior to 0.3.0, PUT /sessions/sessionid/agent checks LEVELEDIT permission for a session but does not reject a bound shared or template agent whose agent.sessionid is None. An authenticated user with ed...

WordPress AI Agent by SiteGround plugin <= 1.2.7 - Missing Authorization to Authenticated (Contributor+) Arbitrary Media Upload via /generate-content REST Endpoint vulnerability

Missing Authorization to Authenticated Contributor+ Arbitrary Media Upload via /generate-content REST Endpoint vulnerability discovered by Wordfence PRISM - Wordfence in WordPress Plugin SG AI Studio versions = 1.2.7...

CVE-2026-18482

Neo.mjs contains a command injection vulnerability within the FileSystemService.mjs component of the ai/mcp/server/file-system MCP server, where the checkSyntax and runPlaywrightTest functions unsafely interpolate caller-controlled absolutePath values into shell commands, enabling arbitrary OS...

CVE-2026-18482 CVE-2026-18482

Neo.mjs contains a command injection vulnerability within the FileSystemService.mjs component of the ai/mcp/server/file-system MCP server, where the checkSyntax and runPlaywrightTest functions unsafely interpolate caller-controlled absolutePath values into shell commands, enabling arbitrary OS...

CVE-2026-17153

The AI Agent by SiteGround plugin for WordPress is vulnerable to authorization bypass in all versions up to, and including, 1.2.7. This is due to the plugin not properly verifying that a user is authorized to perform an action. This makes it possible for unauthenticated attackers to upload images...

CVE-2026-17153

AI Agent by SiteGround plugin (≤1.2.7) has a missing authorization check on its /generate-content REST endpoint, allowing authenticated Contributor-level users to upload images to the media library despite lacking the upload_files capability. The sg_ai_studio_gutenberg_nonce is issued to any bloc...

CVE-2026-17153 AI Agent by SiteGround <= 1.2.7 - Missing Authorization to Authenticated (Contributor+) Arbitrary Media Upload via /generate-content REST Endpoint

The AI Agent by SiteGround plugin for WordPress is vulnerable to authorization bypass in all versions up to, and including, 1.2.7. This is due to the plugin not properly verifying that a user is authorized to perform an action. This makes it possible for unauthenticated attackers to upload images...

EUVD-2026-63200

The AI Agent by SiteGround plugin for WordPress is vulnerable to authorization bypass in all versions up to, and including, 1.2.7. This is due to the plugin not properly verifying that a user is authorized to perform an action. This makes it possible for unauthenticated attackers to upload images...

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...

AI "Mind Viruses" Can Spread Between Agents Through Persistent Prompt Files

Security researchers at Anthropic and Switzerland's EPFL have demonstrated that self-propagating payloads can spread from one artificial intelligence AI agent to the next through the editable system prompt files that autonomous agent harnesses use to carry state between sessions. The work, releas...

How MCP Servers Can Expose Enterprise Secrets

MCP servers can expose enterprise secrets through plaintext configuration files, over-permissioned access and prompt injection, often before security teams even know the server is running. As more organizations adopt AI agents into their systems, that exposure can silently become a major gap in M...

MAL-2026-14070 Malicious code in @ai-vertical/ai-agent (npm)

--- -= Per source details. Do not edit below this line.=- Source: amazon-inspector f3daa0f3fabdeebe3db0146233d623d65ae16aea601e54fd6519a160db5af8ee On require/import, index.js fetches a hardcoded GitHub Gist gist.github.com/aiverticalsolutions/7676451d2f972137d2482c4a8937a77a via the api.github.c...

AI Genie in the Wild

When I give talks about AI genies, I use this sort of example as a hypothetical. It's happened. The story is from Australia. Someone named Andrew tasked OpenClaw to book gym classes for him. And…. Minutes later, his AI agent reported it had discovered a way to book Andrew into classes several wee...

Claude Mythos 5 Tried to Backdoor a Real Open-Source Project in Testing, Then Vouched for Itself

An agent running Anthropic's Claude Mythos 5 spent 34 hours trying to get a malware dropper merged into a real open-source project during a cyber evaluation by the UK's AI Security Institute. When a bystander publicly warned that the code was malicious, the agent denied it, force-pushed a rewritt...