AI Security & LLM Threat Collection

2026-07-21 · MEDIUM

New ENCFORGE Ransomware Targets AI Model Files in Langflow RCE Attack

2026-07-20 · MEDIUM

JadePuffer agentic attacks now target AI model data with ransomware

2026-07-20 · MEDIUM

Would you leave a comfortable Network Security role for AI Security?

2026-07-20 · HIGH

Hugging Face breached by autonomous AI agent

2026-07-20 · HIGH

Capital One Open Sources AI-Powered VulnHunter Security Tool

2026-07-20 · MEDIUM

⚡ Weekly Recap: WordPress RCE, SonicWall 0-Days, AI Service Attacks, SharePoint 0-Day and More

2026-07-20 · HIGH

World's Largest AI Model Repository Hugging Face Breached by Autonomous AI Agent

2026-07-20 · HIGH

Nearly half of open-source AI projects never reach production

2026-07-20 · MEDIUM

Capital One Open Sources AI-Powered ‘VulnHunter’ Security Tool

2026-07-19 · HIGH

CVE-2026-15322: IBM Engineering AI Hub 1.0.0, 1.1.0, and 1.2.0 could allow a remote attacker to obtain sensitive information due to the

CVE-2026-15322

2026-07-19 · HIGH

CVE-2026-15091: IBM Engineering AI Hub 1.0.0, 1.1.0, and 1.2.0 could allow a remote attacker to execute arbitrary scripts due to imprope

CVE-2026-15091

2026-07-19 · HIGH

CVE-2026-58195: Agentic-Flow is an AI agent orchestration platform. Prior to 2.0.14, agentic-flow MCP server tools in src/mcp/standalone

CVE-2026-58195

2026-07-19 · MEDIUM

What AI cyber security platforms are spearheading the field.

2026-07-19 · HIGH

CVE-2026-57860: ForgeCode (tailcallhq/forgecode), an AI pair-programming CLI, automatically loads and executes the MCP servers defined i

CVE-2026-57860

2026-07-18 · MEDIUM

White House launches AI-driven "Gold Eagle" clearinghouse to centralize public-private vulnerability coordination

2026-07-17 · MEDIUM

AI security project: PromptShield

2026-07-17 · MEDIUM

Podcast: Broken Governance, Agentic AI, and the MindStone Agent Exclusive

2026-07-17 · MEDIUM

E.U. Orders Google to Open Android Mic, Camera and Screen to Rival AI Assistants

2026-07-17 · MEDIUM

If you've given an AI agent real credentials, how are you scoping what it can reach?

2026-07-16 · HIGH

MCP Python SDK: WebSocket server transport does not support Host/Origin validation

CVE-2026-59950CVE-2026-59950

2026-07-16 · HIGH

MCP Python SDK: HTTP transports serve session requests without verifying the authenticated principal

CVE-2026-52869CVE-2026-52869

2026-07-16 · HIGH

MCP Python SDK: Experimental task handlers allow any client to access and cancel other clients' tasks

CVE-2026-52870CVE-2026-52870

2026-07-16 · MEDIUM

Claude Chrome extension flaw lets malicious extensions trigger AI actions

2026-07-16 · MEDIUM

With AI, Your Entire Internet History is Attributable to you Personally

2026-07-16 · MEDIUM

Top 10 Data Center and AI Infrastructure Security Risks

2026-07-16 · MEDIUM

AI Data Centers Are Being Built Faster Than They Can Be Secured

2026-07-16 · MEDIUM

Please Stop Making Me Opt Out of AI

2026-07-16 · MEDIUM

AI Agent for reconaissasion

2026-07-15 · HIGH

@andrea9293/mcp-documentation-server: Web UI API binds to all interfaces without authentication by default

CVE-2026-54504CVE-2026-54504

2026-07-15 · MEDIUM

TuxBot v3 Evolution Shows Signs of LLM-Assisted IoT Botnet Development

2026-07-15 · HIGH

LangBot: Authenticated RCE Via MCP Configuration

CVE-2026-54449CVE-2026-54449

2026-07-15 · MEDIUM

Is 'Tech-xit' Imminent? UK Steps Up Sovereignty Push Amid AI Strife

2026-07-15 · MEDIUM

White House Launches AI-Driven ‘Gold Eagle’ Vulnerability Coordination Initiative

2026-07-14 · HIGH

NetLicensing-MCP: Unauthenticated Use of Server-Side NetLicensing API Key in HTTP Mode

CVE-2026-54446CVE-2026-54446

2026-07-14 · HIGH

yutu: Arbitrary File Write via MCP `caption-download` Tool

CVE-2026-50158CVE-2026-50158

2026-07-14 · MEDIUM

Microsoft Patch Tuesday July 2026 - The AI Acopolypse is Here , (Tue, Jul 14th)

2026-07-14 · MEDIUM

Frontier AI: The Genie's Out of the Bottle, But Where's the Rulebook?

2026-07-14 · MEDIUM

Source-reviewing 200+ self-hosted multi-tenant AI/SaaS apps for tenant isolation: 78 leaked across tenants (the "un-retrofitted read sibling")

2026-07-14 · MEDIUM

Enhancing the Threat Intelligence AI Model with Technical Knowledge About Windows Kernel Mode Malware

2026-07-13 · MEDIUM

ExporTheft: 11 "AI Chat Exporter" Chrome extensions upload full chat content on PDF export, while the store listing says "No uploads to external servers"

2026-07-13 · MEDIUM

Context Bombs: Using AI Guardrails as a defensive mechanism

2026-07-13 · MEDIUM

'Yellow Teams' Are Defining the Future of AI Security

2026-07-13 · MEDIUM

Every AI coding agent writes the secrets you paste straight to a plaintext history file — and nobody scans it

2026-07-13 · MEDIUM

Now, defenders are embracing the prompt injection, too

2026-07-13 · MEDIUM

⚡ Weekly Recap: ShareFile Threat, Citrix Bleed 2 Ransomware, AI Coding Attacks, and More

2026-07-13 · MEDIUM

A hardware security AI assistant that checks chips for hidden backdoors

2026-07-13 · MEDIUM

Participants Needed: Master's Research on AI Governance & the EU AI Act

2026-07-12 · MEDIUM

IT Governance vs AI Governance

2026-07-12 · MEDIUM

What's stopping big orgs to replicate those AI Security startups themselves?

2026-07-12 · MEDIUM

Microsoft is rewriting Windows patch guidance because of AI - Help Net Security

2026-07-11 · MEDIUM

Looking for Cybersecurity Contributors – Building an Open-Source AI Bot Detection Project

2026-07-11 · MEDIUM

Freelancing on cybersec/ai

2026-07-11 · MEDIUM

'Ghostcommit' hides prompt injection in images to fool AI agents, steal secrets

2026-07-11 · MEDIUM

A degree in CS or AI engineering & robotics

2026-07-10 · HIGH

mcp-atlassian: Arbitrary server-side file read via attachment upload

2026-07-10 · HIGH

mcp-atlassian: Arbitrary file read via missing path validation in confluence_upload_attachment

2026-07-10 · MEDIUM

Training recommendations for SOC teams in the age of AI?

2026-07-10 · MEDIUM

The Replicant in Your Directory: AI Agents and the Identity Security Gap

2026-07-10 · MEDIUM

AI Coding: Do Security Risks Outweigh Productivity Gains?

2026-07-10 · MEDIUM

Crypto Investigations using AI

2026-07-10 · MEDIUM

Can AI imitate APT behavior well enough to confuse attribution?

2026-07-10 · MEDIUM

Can AI-generated adversaries break TTP-based attribution? (arXiv 2026)

2026-07-10 · MEDIUM

'HalluSquatting' Turns AI Hallucinations Into Botnet Delivery Mechanism

2026-07-10 · MEDIUM

New research: Why no single AI agent harness wins every cybersecurity task

2026-07-10 · MEDIUM

"Comment stuffing" in an HTML phishing attachment as a mechanism for evading AI-based detection?, (Fri, Jul 10th)

2026-07-10 · MEDIUM

‘HalluSquatting’ Turns AI Hallucinations Into Botnet Delivery Mechanism

2026-07-09 · MEDIUM

Microsoft expects more Windows security updates from AI-discovered flaws

2026-07-09 · MEDIUM

New Forg365 phishing platform uses AI to target Microsoft 365 accounts

2026-07-09 · MEDIUM

UK Government Rolls Out Agentic AI Defense Plan Alongside Industry Pledge

2026-07-09 · HIGH

Phantom: Arbitrary file write and decode-bomb DoS via unconfined MCP tool paths

2026-07-09 · MEDIUM

AI Gateways Offer Attackers the Keys to the Kingdom

2026-07-09 · MEDIUM

AI Attacks Move in Minutes. Join This Webinar on Building a Defense That Keeps Up

2026-07-09 · MEDIUM

MOD REQUEST: Can you ban the excessive AI posters please?

2026-07-09 · MEDIUM

AI Coding Tools Tricked Into Hacking Developer Machine via Decades-Old Technique

2026-07-08 · MEDIUM

Lone Attacker Uses AI to Breach AWS Cloud Environment in 72 Hours

2026-07-08 · MEDIUM

AI agents went from "cool demo" to "exploiting CVEs in 10 hours"

2026-07-08 · MEDIUM

Are companies thinking about insurance/liability for AI tool usage, or is that not on the radar yet?

2026-07-08 · MEDIUM

AI Coding Agents Found Triggering Endpoint Security Rules Built to Catch Attackers

2026-07-08 · MEDIUM

HPC AI Workloads Need Runtime Security. The Architecture Already Exists.

2026-07-08 · MEDIUM

Researchers Find New GhostApproval Bug in Many AI Coding Assistants

2026-07-08 · MEDIUM

Google Dialogflow CX Bug Allowed Attackers to Hijack AI Conversations

2026-07-08 · MEDIUM

Critical Vulnerability Exposes GitHub Agentic Workflows to Prompt Injection

2026-07-07 · MEDIUM

Dialogflow CX 'Rogue Agent' Flaw Enabled AI Chatbot Data Theft

2026-07-07 · HIGH

Better Auth has stored XSS in the auth-server origin via javascript: redirect_uri in oidc-provider and mcp

2026-07-07 · MEDIUM

Open-source AI security risk register mapped to MITRE ATLAS, OWASP LLM/Agentic Apps, and NIST AI 100-2

2026-07-07 · MEDIUM

Checkmarx MCP

2026-07-06 · HIGH

Coder's AI Bridge Proxy skips TLS certificate verification in default configuration

CVE-2026-55436CVE-2026-55436

2026-07-06 · HIGH

flyto-core has Unauthenticated Command Execution via HTTP MCP `execute_module`

CVE-2026-55786CVE-2026-55786

2026-07-06 · MEDIUM

Cybersecurity firm says it found 'the first documented case' of AI agentic ransomware

2026-07-06 · MEDIUM

Local test harness for AI browser instruction-boundary failures

2026-07-06 · MEDIUM

Prompt Injection Attacks Trick AI Agents Into Making Crypto Payments

2026-07-06 · MEDIUM

New ENCFORGE Ransomware Targets AI Model Files in Langflow RCE Attack

JadePuffer agentic attacks now target AI model data with ransomware

Would you leave a comfortable Network Security role for AI Security?

Hugging Face breached by autonomous AI agent

Capital One Open Sources AI-Powered VulnHunter Security Tool

⚡ Weekly Recap: WordPress RCE, SonicWall 0-Days, AI Service Attacks, SharePoint 0-Day and More

World's Largest AI Model Repository Hugging Face Breached by Autonomous AI Agent

Nearly half of open-source AI projects never reach production

Capital One Open Sources AI-Powered ‘VulnHunter’ Security Tool

CVE-2026-15322: IBM Engineering AI Hub 1.0.0, 1.1.0, and 1.2.0 could allow a remote attacker to obtain sensitive information due to the

CVE-2026-15091: IBM Engineering AI Hub 1.0.0, 1.1.0, and 1.2.0 could allow a remote attacker to execute arbitrary scripts due to imprope

CVE-2026-58195: Agentic-Flow is an AI agent orchestration platform. Prior to 2.0.14, agentic-flow MCP server tools in src/mcp/standalone

What AI cyber security platforms are spearheading the field.

CVE-2026-57860: ForgeCode (tailcallhq/forgecode), an AI pair-programming CLI, automatically loads and executes the MCP servers defined i

White House launches AI-driven "Gold Eagle" clearinghouse to centralize public-private vulnerability coordination

AI security project: PromptShield

Podcast: Broken Governance, Agentic AI, and the MindStone Agent Exclusive

E.U. Orders Google to Open Android Mic, Camera and Screen to Rival AI Assistants

If you've given an AI agent real credentials, how are you scoping what it can reach?

MCP Python SDK: WebSocket server transport does not support Host/Origin validation

MCP Python SDK: HTTP transports serve session requests without verifying the authenticated principal

MCP Python SDK: Experimental task handlers allow any client to access and cancel other clients' tasks

Claude Chrome extension flaw lets malicious extensions trigger AI actions

With AI, Your Entire Internet History is Attributable to you Personally

Top 10 Data Center and AI Infrastructure Security Risks

AI Data Centers Are Being Built Faster Than They Can Be Secured

Please Stop Making Me Opt Out of AI

AI Agent for reconaissasion

@andrea9293/mcp-documentation-server: Web UI API binds to all interfaces without authentication by default

TuxBot v3 Evolution Shows Signs of LLM-Assisted IoT Botnet Development

LangBot: Authenticated RCE Via MCP Configuration

Is 'Tech-xit' Imminent? UK Steps Up Sovereignty Push Amid AI Strife

White House Launches AI-Driven &#8216;Gold Eagle&#8217; Vulnerability Coordination Initiative

NetLicensing-MCP: Unauthenticated Use of Server-Side NetLicensing API Key in HTTP Mode

yutu: Arbitrary File Write via MCP `caption-download` Tool

Microsoft Patch Tuesday July 2026 - The AI Acopolypse is Here , (Tue, Jul 14th)

Frontier AI: The Genie's Out of the Bottle, But Where's the Rulebook?

Source-reviewing 200+ self-hosted multi-tenant AI/SaaS apps for tenant isolation: 78 leaked across tenants (the &quot;un-retrofitted read sibling&quot;)

Enhancing the Threat Intelligence AI Model with Technical Knowledge About Windows Kernel Mode Malware

ExporTheft: 11 &quot;AI Chat Exporter&quot; Chrome extensions upload full chat content on PDF export, while the store listing says &quot;No uploads to external servers&quot;

Context Bombs: Using AI Guardrails as a defensive mechanism

'Yellow Teams' Are Defining the Future of AI Security

Every AI coding agent writes the secrets you paste straight to a plaintext history file — and nobody scans it

Now, defenders are embracing the prompt injection, too

⚡ Weekly Recap: ShareFile Threat, Citrix Bleed 2 Ransomware, AI Coding Attacks, and More

A hardware security AI assistant that checks chips for hidden backdoors

Participants Needed: Master's Research on AI Governance &amp; the EU AI Act

IT Governance vs AI Governance

What's stopping big orgs to replicate those AI Security startups themselves?

Microsoft is rewriting Windows patch guidance because of AI - Help Net Security

Looking for Cybersecurity Contributors – Building an Open-Source AI Bot Detection Project

Freelancing on cybersec/ai

'Ghostcommit' hides prompt injection in images to fool AI agents, steal secrets

A degree in CS or AI engineering &amp; robotics

mcp-atlassian: Arbitrary server-side file read via attachment upload

mcp-atlassian: Arbitrary file read via missing path validation in confluence_upload_attachment

Training recommendations for SOC teams in the age of AI?

The Replicant in Your Directory: AI Agents and the Identity Security Gap

AI Coding: Do Security Risks Outweigh Productivity Gains?

Crypto Investigations using AI

Can AI imitate APT behavior well enough to confuse attribution?

Can AI-generated adversaries break TTP-based attribution? (arXiv 2026)

'HalluSquatting' Turns AI Hallucinations Into Botnet Delivery Mechanism

New research: Why no single AI agent harness wins every cybersecurity task

"Comment stuffing" in an HTML phishing attachment as a mechanism for evading AI-based detection&#x3f;, (Fri, Jul 10th)

&#8216;HalluSquatting&#8217; Turns AI Hallucinations Into Botnet Delivery Mechanism

Microsoft expects more Windows security updates from AI-discovered flaws

New Forg365 phishing platform uses AI to target Microsoft 365 accounts

UK Government Rolls Out Agentic AI Defense Plan Alongside Industry Pledge

Phantom: Arbitrary file write and decode-bomb DoS via unconfined MCP tool paths

AI Gateways Offer Attackers the Keys to the Kingdom

AI Attacks Move in Minutes. Join This Webinar on Building a Defense That Keeps Up

MOD REQUEST: Can you ban the excessive AI posters please?

AI Coding Tools Tricked Into Hacking Developer Machine via Decades-Old Technique

Lone Attacker Uses AI to Breach AWS Cloud Environment in 72 Hours

AI agents went from &quot;cool demo&quot; to &quot;exploiting CVEs in 10 hours&quot;

Are companies thinking about insurance/liability for AI tool usage, or is that not on the radar yet?

AI Coding Agents Found Triggering Endpoint Security Rules Built to Catch Attackers

HPC AI Workloads Need Runtime Security. The Architecture Already Exists.

White House Launches AI-Driven ‘Gold Eagle’ Vulnerability Coordination Initiative

Source-reviewing 200+ self-hosted multi-tenant AI/SaaS apps for tenant isolation: 78 leaked across tenants (the "un-retrofitted read sibling")

ExporTheft: 11 "AI Chat Exporter" Chrome extensions upload full chat content on PDF export, while the store listing says "No uploads to external servers"

Participants Needed: Master's Research on AI Governance & the EU AI Act

A degree in CS or AI engineering & robotics

"Comment stuffing" in an HTML phishing attachment as a mechanism for evading AI-based detection?, (Fri, Jul 10th)

‘HalluSquatting’ Turns AI Hallucinations Into Botnet Delivery Mechanism

AI agents went from "cool demo" to "exploiting CVEs in 10 hours"