PT-2026-60843

Name of the Vulnerable Software and Affected Versions IBM Engineering AI Hub versions 1.0.0 through 1.2.0 Description Improper neutralization of input during web page generation allows a remote attacker to execute arbitrary scripts. This issue is a Cross-Site Scripting XSS flaw, where malicious...

MAL-2026-10736 Malicious code in memtry-cli (npm)

--- -= Per source details. Do not edit below this line.=- Source: amazon-inspector 11638a6b1b7876a94ef23285cb88f0127c003bb5e4d786dbaba5c30a9cbdfdb7 memtry-cli installs an MCP server whose memtryonboarding tool returns a prompt that instructs the connected AI agent to scan the installer's home...

MAL-2026-10722 Malicious code in @whalent/agent-core (npm)

--- -= Per source details. Do not edit below this line.=- Source: amazon-inspector d8865ae7d25a498766280337f12ceea445a92bd6a6565e668651a79dbcc152e9 The package's main/bin entry dist/index.cjs implements a remote agent that opens a WebSocket to a gateway configured via WHALENTGATEWAY / WHALENTTOKE...

Using Microsegmentation to Contain Autonomous AI Agents

Discover why traditional security fails against autonomous AI agents and how machine-speed microsegmentation helps stop tool chaining and lateral movement...

Least privilege for AI agents: Identity, access, and tool binding

In this article 1. Real-world scenarios 2. Best Practices: Identity + RBAC + Scope + Safe Tool Binding 3. Looking Ahead AI agents aren't only smarter API callers. They plan, chain actions across systems, and invoke tools in sequences while no single human explicitly approves each step. The...

Least privilege for AI agents: Identity, access, and tool binding

In this article 1. Real-world scenarios 2. Best Practices: Identity + RBAC + Scope + Safe Tool Binding 3. Looking Ahead AI agents aren't only smarter API callers. They plan, chain actions across systems, and invoke tools in sequences while no single human explicitly approves each step. The...

AI Can Find Bugs, But Human Knowledge Still Proves Them

Artificial intelligence AI is changing offensive security, but it has not changed the standard that matters most: a finding has to be proven before it becomes useful. AI-assisted tools can read code quickly, generate payloads, summarize attack surfaces, explain unfamiliar APIs, and run repetitive...

The Hunter's Paradox: Is it time to embrace automated threat hunting?

Should we let AI run our threat hunts? The debate usually splits into two camps. One says, "Yes, obviously! The sheer scale of our security telemetry is impossible for humans to deal with." The other says, "Absolutely not! You can't trust an AI with something this important." The thing is, I thin...

EUVD-2026-44893

The WPBot – AI ChatBot for Live Support, Lead Generation, AI Services plugin for WordPress is vulnerable to authorization bypass in all versions up to, and including, 8.5.6. This is due to the plugin not properly verifying that a user is authorized to perform an action. This makes it possible for...

CVE-2026-12510

The AI Engine WordPress plugin before 3.5.5 does not verify that a user owns the chatbot conversation referenced by a client-supplied identifier, allowing users with subscriber-level access to read other users' private conversations and take over their conversation records when the discussions...

EUVD-2026-44870

The BetterDocs WordPress plugin before 4.5.5 does not sanitise an AI-generated documentation summary before storing and outputting it, and the feature that generates it is exposed to unauthenticated users, allowing them to store a malicious payload via prompt injection that executes in the browse...

PT-2026-60416

The AI Engine WordPress plugin before 3.5.5 does not verify that a user owns the chatbot conversation referenced by a client-supplied identifier, allowing users with subscriber-level access to read other users' private conversations and take over their conversation records when the discussions...

A Bootiful Podcast: Russ Miles on Safer, More Productive Interactions with AI

I’m joined, I think, for the second time by my friend, the legendary architect and developer extraordinaire Russ Miles, who has given some of the most cerebral and exciting Spring keynotes and talks ever. And this time, he’s back to talk about — guess what — A.I. As usual, he’s got a different an...

CVE-2026-57833

The CVE affects the Joomla extension 4Analytics for weeblr.com, with an unauthenticated stored XSS vulnerability in the AI analysis feature present in versions prior to 5.0.2. The underlying issue is a stored XSS in the AI analysis workflow, leading to high impact on confidentiality, integrity, a...

CVE-2026-57833 Joomla Extension - weeblr.com - Unauthenticated stored XSS in 4Analytics < 5.0.2

Joomla Extension - weeblr.com - Unauthenticated stored XSS in 4Analytics 5.0.2 - The Joomla extension 4Analytics is vulnerable to an unauthenticated stored XSS in relation to the AI analysis feature...

MAL-2026-10629 Malicious code in ai-pro-sdk (npm)

--- -= Per source details. Do not edit below this line.=- Source: amazon-inspector b035f137addcf0118c3d042ece322d0fdde054e4ed283317d3b2adb309e38689 [email protected] is advertised as a Vercel AI SDK provider for Claude via the Claude Agent SDK, but the published tarball ships no code: package.json...

Adversarial Prompting Framework for AI Safety Assessment

Artificial Intelligence AI, especially Generative AI GenAI, adoption has increased in industries significantly in recent years. However, the use of these models may also expose systems to new forms of cyberattacks by different malicious actors -- adversarial prompt attack APA being one of the mos...

How Pentera Turns AI Security Workflows into Validation Engines

AI security agents are starting to influence real security decisions. They summarize findings, prioritize remediation, recommend next steps, and help teams move faster. But most still rely on fragmented risk signals: scanner output, severity scores, threat intelligence, configuration findings, an...

EUVD-2026-43547

9Router through version 0.4.41 contain an unauthenticated information disclosure vulnerability that allows remote attackers to retrieve plaintext API keys for all connected AI provider accounts by sending a single unauthenticated request to the /api/usage/stats endpoint. Attackers can exploit the...

Six Minutes to Compromise: How ‘Patriot Bait’ Actor Used AI to Build and Deploy a C&C Botnet

TrendAI™ Research analyzed over 200 Gemini CLI session logs showing how a Russian-speaking threat actor used AI to run a live botnet, finishing a full C&C migration in six minutes while doing just 11% of the work himself...