FBI Warns Russian Intelligence Hackers Target Signal Backup Recovery Keys

The FBI and CISA have updated their March warning about Russian intelligence phishing Signal accounts, and the operators have added a step: they now coax targets into handing over their Signal Backup Recovery Key. Hand it over once, and the attacker can restore the account's backup, read the...

CVE-2025-32394

AutoGPT is a workflow automation platform for creating, deploying, and managing continuous artificial intelligence agents. Prior to 0.6.32, there is a DoS vulnerability in AITextSummarizerBlock. Malicious users can amplify their input. For example, if a malicious user inputs 10K of content, the...

Protection Mechanism Failure

Overview Affected versions of this package are vulnerable to Protection Mechanism Failure via the rendering of AI bot tool result posts containing injected markdown image syntax. An attacker can exfiltrate data to an attacker-controlled server by crafting malicious content that is rendered by a...

PYSEC-2026-2146

Docling simplifies document processing by parsing diverse formats and providing integrations with the generative AI ecosystem. Prior to 2.94.0, the HTML backend has unsafe URI and path handling. This vulnerability is fixed in 2.94.0...

EUVD-2025-210364

AutoGPT is a workflow automation platform for creating, deploying, and managing continuous artificial intelligence agents. Prior to 0.6.32, there is a DoS vulnerability in AITextSummarizerBlock. Malicious users can amplify their input. For example, if a malicious user inputs 10K of content, the...

CVE-2025-32394

Technical details are not publicly available in the provided documents. Monitor for updates.

EUVD-2026-39791

Docling simplifies document processing by parsing diverse formats and providing integrations with the generative AI ecosystem. Prior to 2.94.0, the HTML backend has unsafe URI and path handling. This vulnerability is fixed in 2.94.0...

Important: Red Hat Security Advisory: Red Hat AI Inference Server Model Optimization Tools 3.3.5 (CUDA)

Red Hat AI Inference Server Model Optimization Tools 3.3.5 CUDA is now available. Red Hat® AI Inference Server Model Optimization Tools...

Beyond IOCs: AI-enabled threat intelligence

Welcome to this week's Threat Source newsletter. The issue of AI in cybersecurity is often portrayed as a binary choice: either a force multiplier for our adversaries, or a tool bringing professional obsolescence. The reality is more nuanced. While AI certainly brings some advantage to attackers,...

Upwind Security Brings AI Visibility to the Endpoint, Unifying Cloud and Device Security

Upwind’s AI Sensor links endpoint activity with cloud context, helping teams track MCP connections, AI actions, identities and developer risk in one view today...

Your AI Cost Model Stops at the Token Price. The Bill Doesn't.

Your AI cost model stops at the token price, but the bill doesn't. Discover why almost 80% of production AI spend sits in inference and how to optimize your setup...

British Police Built a Sprawling Crime-Prediction Machine. Some Results Couldn’t Be Trusted

As UK police embrace the AI revolution, a WIRED investigation reveals the messy inside story of one region’s experiment with predictive analytics...

New Gaslight macOS Malware Uses Prompt Injection to Disrupt AI-Assisted Analysis

A previously undocumented Rust-based macOS implant and information stealer has been found to embed a prompt injection payload designed to trick a malware analyst's artificial intelligence AI tools and trick it into aborting or refusing an analysis of the artifact. The malware has been codenamed...

Application of LLMs to Threat Assessment of Foreign Peacekeeping Missions

We present a novel approach for applying Large Language Models LLMs to threat assessment in the context of foreign peacekeeping missions. Building on the PINPOINT project and its use case, the EU Monitoring Mission in Georgia, we combine an interdisciplinary risk-model with OSINT-based media...

Malicious code in rstreams-metrics (npm)

The rstreams-metrics npm package was compromised as part of the Miasma worm campaign targeting the LeoPlatform npm ecosystem. On June 24, 2026, 20 LeoPlatform packages were published within a 3-second window by a threat actor who had taken over the npm account czirker belonging to the LeoPlatform...

MAL-2026-6436 Malicious code in solo-nav (npm)

The solo-nav npm package was compromised as part of the Miasma worm campaign targeting the LeoPlatform npm ecosystem. On June 24, 2026, 20 LeoPlatform packages were published within a 3-second window by a threat actor who had taken over the npm account czirker belonging to the LeoPlatform...

CVE-2026-55583

Twenty is an open-source CRM customer relationship management platform. Prior to 2.9.0, Twenty was vulnerable to a cross-workspace insecure direct object reference IDOR in the AI agent monitor's AgentTurnResolver, in packages/twenty-server/src/engine/metadata-modules/ai/ai-agent-monitor/reso...

CVE-2026-55583 Twenty: Cross-workspace IDOR in AgentTurnResolver

Twenty is an open-source CRM customer relationship management platform. Prior to 2.9.0, Twenty was vulnerable to a cross-workspace insecure direct object reference IDOR in the AI agent monitor's AgentTurnResolver, in packages/twenty-server/src/engine/metadata-modules/ai/ai-agent-monitor/reso...

DRUPAL-CONTRIB-2026-057

This module provides the entity type and runtime for Drupal AI Agents, enabling agents to use tools. Under certain circumstances, the agent inherits deterministic parameters when invoking the same tool in one request, which can lead to information disclosure...

DRUPAL-CONTRIB-2026-054

The module and certain submodules AI Automators, AI Translate, AI API Explorer, AI Content Suggestions provide the ability to use an LLM to generate HTML or Markdown and preview it in a browser. Under certain circumstances, rendering of this HTML can lead to Cross Site Scripting, or exposing secr...