aisecwatch.com
DashboardVulnerabilitiesNewsResearchArchiveStatsDatasetFor devs
Subscribe
aisecwatch.com

Real-time AI security monitoring. Tracking AI-related vulnerabilities, safety and security incidents, privacy risks, research developments, and policy changes.

Navigation

VulnerabilitiesNewsResearchDigest ArchiveNewsletter ArchiveSubscribeData SourcesStatisticsDatasetAPIIntegrationsWidgetRSS Feed

Maintained by

Truong (Jack) Luu

Information Systems Researcher

AI Sec Watch

The security intelligence platform for AI teams

AI security threats move fast and get buried under hype and noise. Built by an Information Systems Security researcher to help security teams and developers stay ahead of vulnerabilities, privacy incidents, safety research, and policy developments.

Independent research. No sponsors, no paywalls, no conflicts of interest.

[TOTAL_TRACKED]
3,710
[LAST_24H]
1
[LAST_7D]
1
Daily BriefingSaturday, May 16, 2026

No new AI/LLM security issues were identified today.

Latest Intel

page 74/371
VIEW ALL
01

The agentic SOC—Rethinking SecOps for the next decade

securityindustry
Apr 9, 2026

The agentic SOC is a new operating model where security operations centers use AI agents (software programs that can act autonomously) and automated defenses to respond to threats faster and more independently, rather than waiting for human analysts to handle every alert. Instead of reacting to individual incidents, this approach anticipates cyberattacker movements and automatically takes defensive actions, freeing human analysts to focus on strategic decisions and deeper investigation.

Microsoft Security Blog
02

CVE-2026-39981: AGiXT is a dynamic AI Agent Automation Platform. Prior to 1.9.2, the safe_join() function in the essential_abilities ext

security
Apr 9, 2026

AGiXT, a platform for automating AI agents, has a vulnerability in its safe_join() function (a tool meant to safely combine file paths) that fails to check whether file paths stay within the agent's allowed workspace. Before version 1.9.2, an authenticated attacker could use directory traversal sequences (special path tricks like '../' to navigate outside intended folders) to read, write, or delete files on the server.

Fix: Update AGiXT to version 1.9.2, where this vulnerability is fixed.

NVD/CVE Database
03

Google’s Gemini AI can answer your questions with 3D models and simulations

industry
Apr 9, 2026

Google has upgraded Gemini, its AI chatbot, to generate interactive 3D models and simulations in response to user questions. Users can rotate these models, adjust sliders to change parameters, and input different values to see real-time changes in the simulation.

The Verge (AI)
04

GHSA-3vvq-q2qc-7rmp: OpenClaw B-M3: ClawHub package downloads are not enforced with integrity verification

security
Apr 9, 2026

OpenClaw, a user-controlled local assistant, had a vulnerability where ClawHub package downloads didn't verify the integrity of downloaded files (a security check ensuring files haven't been tampered with). This meant malicious or corrupted plugin archives could be installed without detection. The vulnerability affected OpenClaw versions 2026.4.1 and earlier.

Fix: Update to OpenClaw npm package version 2026.4.8 or later. The fix is also available in the main branch at commit d7c3210cd6f5fdfdc1beff4c9541673e814354d5.

GitHub Advisory Database
05

GHSA-67mf-f936-ppxf: OpenClaw `node.pair.approve` placed in `operator.write` scope instead of `operator.pairing` allows unprivileged pairing approval

security
Apr 9, 2026

OpenClaw (a local AI assistant software) had a security bug where the `node.pair.approve` function checked for `operator.write` permissions instead of the more restrictive `operator.pairing` scope, allowing users without proper authorization to approve device pairing on executive-capable nodes. This vulnerability only affects OpenClaw in its single-user trust model and does not impact multi-tenant services.

Fix: Update OpenClaw to version 2026.4.8 or later. The fix is available in the npm package and has been verified in commit d7c3210cd6f5fdfdc1beff4c9541673e814354d5 on the main branch.

GitHub Advisory Database
06

GHSA-5h3f-885m-v22w: OpenClaw: Existing WS sessions survive shared gateway token rotation

security
Apr 9, 2026

OpenClaw, a local AI assistant, had a security flaw where WebSocket sessions (persistent connections that allow real-time communication between a client and server) using a shared gateway token remained active even after the token was rotated (changed to a new one). This meant that even after administrators changed the authentication token, old sessions could continue operating without re-authenticating.

Fix: Update OpenClaw to version 2026.4.8 or later. The fix is available in the npm package and has been verified in commit d7c3210cd6f5fdfdc1beff4c9541673e814354d5 on the main branch.

GitHub Advisory Database
07

GHSA-cmfr-9m2r-xwhq: OpenClaw `node.invoke(browser.proxy)` bypasses `browser.request` persistent profile-mutation guard

security
Apr 9, 2026

OpenClaw, a user-controlled local assistant, had a security flaw where `node.invoke(browser.proxy)` could bypass the `browser.request` guard and modify persistent browser profiles (stored settings that shouldn't be changed without permission). The vulnerability affected versions up to v2026.04.01.

Fix: Update to patched version `2026.4.8` or later. The fix is available in npm and was verified in commit `d7c3210cd6f5fdfdc1beff4c9541673e814354d5`.

GitHub Advisory Database
08

GHSA-whf9-3hcx-gq54: OpenClaw `device.token.rotate` mints tokens for unapproved roles, bypassing device role-upgrade pairing

security
Apr 9, 2026

OpenClaw's `device.token.rotate` function had a security flaw where it could create tokens with roles (sets of permissions) that hadn't been properly approved through the required pairing process, potentially letting users gain unauthorized access levels. This vulnerability only affects OpenClaw, which is a local assistant software that runs on a user's own device.

Fix: Update OpenClaw to version 2026.4.8 or later. The fix is available in the patched npm version and was merged into the main codebase at commit d7c3210cd6f5fdfdc1beff4c9541673e814354d5.

GitHub Advisory Database
09

OpenAI shelves Stargate UK in blow to Britain’s AI ambitions

policyindustry
Apr 9, 2026

OpenAI has delayed its Stargate UK project, which was a planned major investment in Britain's AI infrastructure as part of a larger UK-US deal announced last September. The company cited high energy costs and regulatory concerns as reasons for the delay, disappointing the British government which had positioned AI development as central to its economic growth strategy.

The Guardian Technology
10

OpenAI pauses UK data centre deal over energy costs and regulation

policyindustry
Apr 9, 2026

OpenAI has paused its UK data centre project called Stargate UK, which would have built a large computing facility in Northumberland to support AI development, citing concerns about high energy costs and regulatory uncertainty. The company stated it will only move forward when conditions improve, though critics note that energy prices and UK AI regulation have not recently changed significantly. This pause is a setback for the UK government's goal to position the country as an AI leader and boost economic growth through tech investment.

BBC Technology
Prev1...7273747576...371Next