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]
6,483
[LAST_24H]
35
[LAST_7D]
153
Daily BriefingTuesday, August 18, 2026
>

OpenAI Launches ChatGPT for Teens with Enhanced Safety Controls: OpenAI introduced a dedicated version of ChatGPT for users aged 13-17 with features including Study Mode (which prompts students to work through problems rather than providing direct answers), human-reviewed parental alerts for harmful requests like eating disorder content, and options to disable human-like voice responses. The rollout comes amid growing pressure on AI platforms to implement age verification and youth-specific protections.

>

LLMs Leak Sensitive Data When Using Persistent Memory: Research found that frontier LLMs (the most advanced current systems) inappropriately share private details from past conversations at rates up to 69% attribute-level violations, even when explicitly instructed to protect privacy. The findings reveal that models struggle to make context-appropriate decisions about what information to share, tending to either overshare or withhold everything rather than apply nuanced judgment.

Latest Intel

page 484/649
VIEW ALL
01

⚡ Weekly Recap: AI Skill Malware, 31Tbps DDoS, Notepad++ Hack, LLM Backdoors and More

securitypolicy
Critical This Week5 issues
critical

GHSA-7gwp-5pfp-969j: MLflow: Unauthenticated full-read SSRF in webhook delivery: _validate_webhook_url bypassed via unvalidated HTTP redirects (and DNS rebinding)

CVE-2026-64849GitHub Advisory DatabaseAug 17, 2026
Aug 17, 2026
>

AI Excels at Finding Zero-Days but Doubles Security Flaw Rates in Generated Code: While LLMs demonstrate growing capability in discovering zero-day vulnerabilities (previously unknown security flaws) and building exploits, AI-generated code contains security weaknesses at roughly twice the rate of human-written code, with 44% containing at least one OWASP Top 10 vulnerability (the most critical categories of code weaknesses). Despite 99% syntax correctness, the asymmetry between AI's offensive and defensive security capabilities remains unexplained.

Feb 9, 2026

This recap highlights how attackers are exploiting trusted tools and marketplaces rather than breaking security controls directly. Key threats include malicious skills appearing in ClawHub (a registry for AI agent add-ons), a record-breaking 31.4 Tbps DDoS attack (a flood attack that overwhelms servers with massive traffic), and compromised update infrastructure for Notepad++ being used to distribute malware. The pattern shows attackers are abusing trust in updates, app stores, and AI workflows to gain access to systems.

Fix: OpenClaw has announced a partnership with Google's VirusTotal malware scanning platform to scan skills uploaded to ClawHub as part of a defense-in-depth approach to improve security. Additionally, the source notes that open-source agentic tools like OpenClaw require users to maintain higher baseline security competence than managed platforms.

The Hacker News
02

LLMs are Getting a Lot Better and Faster at Finding and Exploiting Zero-Days

securityresearch
Feb 9, 2026

Claude Opus 4.6, a new AI model, is significantly better at finding zero-day vulnerabilities (security flaws unknown to vendors and the public) than previous models, discovering high-severity bugs in well-tested code that fuzzing tools (programs that test software by sending random inputs) had missed for years. Unlike traditional fuzzing, Opus 4.6 analyzes code like a human researcher would, studying past fixes and code patterns to reason about what inputs would cause failures.

Schneier on Security
03

CVE-2026-1868: GitLab has remediated a vulnerability in the Duo Workflow Service component of GitLab AI Gateway affecting all versions

security
Feb 9, 2026

GitLab AI Gateway had a vulnerability in its Duo Workflow Service component where user-supplied data wasn't properly validated before being processed (insecure template expansion), allowing attackers to craft malicious workflow definitions that could crash the service or execute code on the Gateway. This flaw affected multiple versions of the AI Gateway.

Fix: Update GitLab AI Gateway to version 18.6.2, 18.7.1, or 18.8.1, depending on which version you are running, as the vulnerability has been fixed in these versions.

NVD/CVE Database
04

OpenClaw Integrates VirusTotal Scanning to Detect Malicious ClawHub Skills

securitysafety
Feb 8, 2026

OpenClaw has partnered with VirusTotal (a malware analysis service owned by Google) to scan skills uploaded to ClawHub, its marketplace for AI agent extensions. The system creates a unique SHA-256 hash (a digital fingerprint) for each skill and checks it against VirusTotal's database, automatically approving benign skills, flagging suspicious ones, and blocking malicious ones, with daily rescans of active skills. However, OpenClaw acknowledged that this scanning is not foolproof and some malicious skills using concealed prompt injection (tricking the AI by hiding malicious instructions in user input) may still get through.

Fix: OpenClaw announced it will publish a comprehensive threat model, public security roadmap, formal security reporting process, and details about a security audit of its entire codebase. Additionally, the platform added a reporting option that allows signed-in users to flag suspicious skills.

The Hacker News
05

Claude: Speed up responses with fast mode

industry
Feb 7, 2026

Anthropic released a faster version of Claude Opus 4.6 that operates 2.5 times faster, accessible through a /fast command in Claude Code, but costs 6 times more than the standard version ($30/million input tokens and $150/million output tokens versus the normal $5/million and $25/million). The company is offering a 50% discount until February 16th, reducing the cost multiplier to 3x during that period, and users can also extend the context window (the amount of text the AI can process at once) to 1 million tokens for additional charges.

Simon Willison's Weblog
06

Moltbook, the Social Network for AI Agents, Exposed Real Humans’ Data

security
Feb 7, 2026

Moltbook, a social network platform for AI agents to interact with each other, had a serious security flaw where a private key (a secret code used to authenticate users) was exposed in its JavaScript code. This exposed thousands of users' email addresses, millions of API credentials (login tokens), and private communications between AI agents, allowing attackers to impersonate any user. The vulnerability is particularly notable because Moltbook's code was entirely written by AI rather than human programmers.

Fix: Moltbook has fixed the security flaw that was discovered by the security firm Wiz.

Wired (Security)
07

CVE-2026-25628: Qdrant is a vector similarity search engine and vector database. From 1.9.3 to before 1.16.0, it is possible to append t

security
Feb 6, 2026

Qdrant (a vector similarity search engine and vector database) has a vulnerability in versions 1.9.3 through 1.15.x where an attacker with read-only access can use the /logger endpoint to append data to arbitrary files on the system by controlling the on_disk.log_file path parameter. This vulnerability allows unauthorized file manipulation with minimal privileges required.

Fix: Update to Qdrant version 1.16.0 or later, where this vulnerability is fixed.

NVD/CVE Database
08

CVE-2026-25592: Semantic Kernel is an SDK used to build, orchestrate, and deploy AI agents and multi-agent systems. Prior to 1.70.0, an

security
Feb 6, 2026

Microsoft's Semantic Kernel SDK (a tool for building AI agents that work together) had a vulnerability before version 1.70.0 that allowed attackers to write arbitrary files (files placed anywhere on a system) through the SessionsPythonPlugin component. The vulnerability has been fixed in version 1.70.0.

Fix: Update to Microsoft.SemanticKernel.Core version 1.70.0. Alternatively, users can create a Function Invocation Filter (a check that runs before function calls) which inspects the arguments passed to DownloadFileAsync or UploadFileAsync and ensures the provided localFilePath is allow listed (checked against an approved list of file paths).

NVD/CVE Database
09

CVE-2026-25533: Enclave is a secure JavaScript sandbox designed for safe AI agent code execution. Prior to 2.10.1, the existing layers o

security
Feb 6, 2026

Enclave is a secure JavaScript sandbox used to safely run code written by AI agents. Before version 2.10.1, attackers could bypass its security protections in three ways: using dynamic property accesses to skip code validation, exploiting how error objects work in Node.js's vm module (a built-in tool for running untrusted code safely), and accessing functions through host object references to escape sandbox restrictions.

Fix: This vulnerability is fixed in version 2.10.1.

NVD/CVE Database
10

CVE-2026-25580: Pydantic AI is a Python agent framework for building applications and workflows with Generative AI. From 0.0.26 to befor

security
Feb 6, 2026

Pydantic AI, a Python framework for building AI applications, has a Server-Side Request Forgery vulnerability (SSRF, where an attacker tricks a server into making requests to unintended internal resources) in versions 0.0.26 through 1.55.x. If an application accepts message history from untrusted users, attackers can inject malicious URLs that make the server request internal services or steal cloud credentials. This only affects apps that take external user input for message history.

Fix: Update Pydantic AI to version 1.56.0 or later, where this vulnerability is fixed.

NVD/CVE Database
Prev1...482483484485486...649Next
critical

CVE-2026-75110: MemOS is a memory operating system for LLMs and AI agents. In deployments where authentication is enabled (AUTH_ENABLED=

CVE-2026-75110NVD/CVE DatabaseAug 17, 2026
Aug 17, 2026
critical

CVE-2026-64859: New API is a large language mode (LLM) gateway and artificial intelligence (AI) asset management system. Prior to 1.0.0-

CVE-2026-64859NVD/CVE DatabaseAug 17, 2026
Aug 17, 2026
critical

CVE-2025-27772: UpTrain is an open-source platform to evaluate and improve generative AI applications. In version 0.7.1 and prior, the `

CVE-2025-27772NVD/CVE DatabaseAug 17, 2026
Aug 17, 2026
critical

CVE-2025-27771: UpTrain is an open-source platform to evaluate and improve generative AI applications. In version 0.7.1 and prior, the `

CVE-2025-27771NVD/CVE DatabaseAug 17, 2026
Aug 17, 2026