20597 matches found
The Governance Gap: How the EU AI Act Makes API Security a Compliance Imperative
Your legal team just handed you a 400-page document and said "figure out compliance." The EU AI Act is live, your organization falls under its scope, which is broader than many expect. Even non‑EU companies must comply if their AI systems are used, deployed, or produce effects within the European...
EUVD-2026-25342
OpenClaw before 2026.4.2 fails to filter Slack thread context by sender allowlist, allowing non-allowlisted messages to enter agent context. Attackers can inject unauthorized thread messages through allowlisted user replies to bypass sender access controls and manipulate model context...
GHSA-7HRG-5W46-5R2X Duplicate Advisory: OpenClaw: Slack thread context could include messages from non-allowlisted senders
Duplicate Advisory This advisory has been withdrawn because it is a duplicate of GHSA-qm77-8qjp-4vcm. This link is maintained to preserve external references. Original Description OpenClaw before 2026.4.2 fails to filter Slack thread context by sender allowlist, allowing non-allowlisted messages ...
Automation-Exploit: A Multi-Agent LLM Framework for Adaptive Offensive Security with Digital Twin-Based Risk-Mitigated Exploitation
The offensive security landscape is highly fragmented: enterprise platforms avoid memory-corruption vulnerabilities due to Denial of Service DoS risks, Automatic Exploit Generation AEG systems suffer from semantic blindness, and Large Language Model LLM agents face safety alignment filters and...
TOTOLINK A3300R hour parameter command injection vulnerability
TOTOLINK A3300R is a wireless router from China's Gion Electronics TOTOLINK. A command injection vulnerability exists in the TOTOLINK A3300R hour parameter, which originates from the cstecgi.cgi file failing to properly validate the hour parameter, and can be exploited by an attacker to execute...
TOTOLINK A3300R stunMinAlive Parameter Command Injection Vulnerability
TOTOLINK A3300R is a wireless router from China's Gion Electronics TOTOLINK. A command injection vulnerability exists in the TOTOLINK A3300R stunMinAlive parameter, which stems from a failure to properly handle the stunMinAlive parameter in cstecgi.cgi, and can be exploited by an attacker to...
PT-2026-34818
Name of the Vulnerable Software and Affected Versions Kirby versions prior to 4.9.0 Kirby versions prior to 5.4.0 Description Kirby is an open-source content management system where user permissions and model blueprint options control authorization for actions such as pages.create, files.create,...
Training a General Purpose Automated Red Teaming Model
Automated methods for red teaming LLMs are an important tool to identify LLM vulnerabilities that may not be covered in static benchmarks, allowing for more thorough probing. They can also adapt to each specific LLM to discover weaknesses unique to it. Most current automated red teaming methods a...
CVE-2026-41358
OpenClaw before 2026.4.2 fails to filter Slack thread context by sender allowlist, allowing non-allowlisted messages to enter agent context. Attackers can inject unauthorized thread messages through allowlisted user replies to bypass sender access controls and manipulate model context...
CVE-2026-41358
OpenClaw is vulnerable before version 2026.4.2. The issue arises because Slack thread context is not properly filtered by the sender allowlist, allowing non-allowlisted messages to enter the agent context. Attackers can inject unauthorized thread messages via allowlisted user replies to bypass se...
CVE-2026-41358
OpenClaw before 2026.4.2 fails to filter Slack thread context by sender allowlist, allowing non-allowlisted messages to enter agent context. Attackers can inject unauthorized thread messages through allowlisted user replies to bypass sender access controls and manipulate model context...
CVE-2026-41358 OpenClaw < 2026.4.2 - Sender Allowlist Bypass via Slack Thread Context
OpenClaw before 2026.4.2 fails to filter Slack thread context by sender allowlist, allowing non-allowlisted messages to enter agent context. Attackers can inject unauthorized thread messages through allowlisted user replies to bypass sender access controls and manipulate model context...
EUVD-2026-25242
An issue was discovered in ToToLink A3300R firmware v17.0.0cu.557B20221024 allowing attackers to execute arbitrary commands via the pppoeMtu parameter to /cgi-bin/cstecgi.cgi...
CVE-2026-31181
An issue was discovered in ToToLink A3300R firmware v17.0.0cu.557B20221024 allowing attackers to execute arbitrary commands via the stunServerAddr parameter to /cgi-bin/cstecgi.cgi...
MINI-7M96-282Q-VFM3
Bulletin has no description...
MINI-38FX-RXC5-2MC5
Bulletin has no description...
MINI-PWM8-JVQC-M73X
Bulletin has no description...
Important: Red Hat Security Advisory: Red Hat Enterprise Linux AI 3.3.1
Red Hat Enterprise Linux AI 3.3.1 is now available. Red Hat® Enterprise Linux® AI is a foundation model platform to seamlessly develop, test, and run Granite family large language models LLMs for enterprise applications...
Project Glasswing Proved AI Can Find the Bugs. Who's Going to Fix Them?
Last week, Anthropic announced Project Glasswing, an AI model so effective at discovering software vulnerabilities that they took the extraordinary step of postponing its public release. Instead, the company has given access to Apple, Microsoft, Google, Amazon, and a coalition of others to find a...
