A prompt injection flaw in Google Gemini’s voice assistant let attackers hide malicious commands in notifications, enabling social engineering and more.
Tag: injection
Global Security News
Malicious Notifications Could Trick Google Gemini Users
A prompt injection flaw in Google Gemini’s voice assistant let attackers hide malicious commands in notifications, enabling social engineering and more.
Global Security News
Drupal bug added to CISA list of known exploited vulnerabilities
Drupal SQL injection flaw CVE-2026-9082 added to CISA KEV as active attacks target sites.
AI, Exploits, Global Security News
Ghost CMS SQL injection flaw exploited in large-scale ClickFix campaign
A large-scale campaign is exploiting a critical SQL injection vulnerability (CVE-2026-26980) in Ghost CMS to inject malicious JavaScript code that triggers ClickFix attack flows. […]
AI, Exploits, Global Security News, Government & Policy, Risk Management
CVE-2026-9082: Drupal’s Highly Critical SQL Injection Flaw Is Already Under Active Attack
Attackers began exploiting Drupal SQL injection flaw CVE-2026-9082 within 48 hours of patch release. Drupal issued a highly critical security patch on May 20 for CVE-2026-9082, a SQL injection vulnerability that allows unauthenticated attackers to compromise sites running PostgreSQL databases. The project maintainers warned ahead of the release that exploits could surface within hours or…
Exploits, Global Security News
Drupal: Critical SQL injection flaw now targeted in attacks
Drupal is warning that hackers are attempting to exploit a “highly critical” SQL injection vulnerability announced earlier this week. […]
AI, Exploits, Global Security News
Patch Now: Critical Flaw in OT Robot OS Gives Attackers Control
An unauthenticated attacker can exploit the command injection vulnerability to gain remote access to robotic systems, causing significant disruption to the environment.
AI, Apps, Exploits, Global Security News, Risk Management
New image-based prompt injection attack targets multimodal AI models
Security researchers have developed a new image-based prompt injection attack that can manipulate how multimodal AI systems interpret user instructions without modifying the original text prompt, potentially expanding security risks for AI agents and vision-language systems. In a research paper published this week, researchers from Xidian University described a technique called “CrossMPI,” which uses nearly…
Global Security News
Avada Builder Flaws Expose One Million WordPress Sites
Avada Builder flaws allowed file read and SQL injection on one million WordPress sites
AI, Global Security News
Google Fixes CVSS 10 Gemini CLI Vulnerability Enabling GitHub Issue-Based RCE
Google patches a CVSS 10 Gemini CLI vulnerability that allowed hackers to use prompt injection and privilege escalation for a full supply chain compromise.
AI, Cybersecurity, Global Security News, Government & Policy, Risk Management
Security agencies draw red lines around agentic AI deployments
With prompt injection and other attack pathways consistently surfacing across agentic AI deployments, security watchdogs have stepped in, collectively, to draw some hard boundaries. A joint advisory from the US Cybersecurity and Infrastructure Security Agency (CISA) and international partners has called for tighter control over permissions, stronger monitoring, and a more deliberate rollout strategy, urging…
AI, Cybersecurity, Exploits, Global Security News
Hackers Use Hidden Website Instructions in New Attacks on AI Assistants
Cybersecurity researchers at Forcepoint uncover new indirect prompt injection attacks that use hidden website code to exploit AI assistants like GitHub Copilot.
AI, Global Security News
Researchers Uncover 10 In-the-Wild Prompt Injection Payloads Targeting AI Agents
Forcepoint has found 10 new indirect prompt injection attacks targeting AI agents
AI, Exploits, Global Security News, malware, Network Security, Risk Management
Mirai Botnet exploits CVE-2025-29635 to target legacy D-Link routers
Mirai botnet is targeting old D-Link routers using CVE-2025-29635, a command injection flaw exploitable via crafted POST requests after public PoC disclosure. A Mirai botnet is actively exploiting a command injection vulnerability, tracked as CVE-2025-29635, in discontinued D-Link routers, Akamai reports. The flaw allows attackers to inject commands because an attacker-controlled value is copied without…
AI, Global Security News
Google Fixes Critical RCE Flaw in AI-Based Antigravity Tool
The prompt injection vulnerability in the agentic AI product for filesystem operations was a sanitization issue that allowed for sandbox escape and arbitrary code execution.
AI, Exploits, Global Security News, Network Security
Prompt injection turned Google’s Antigravity file search into RCE
Security researchers have revealed a prompt injection flaw in Google’s Antigravity IDE that could be weaponized to bypass its sandbox protections and achieve remote code execution (RCE). The issue came from Antigravity’s ability to allow AI agents to invoke native functions, like searching files, on behalf of the user. Designed to kill complexity, the feature…
AI, Global Security News
GrafanaGhost Vulnerability Allows Data Theft via AI Injection
GrafanaGhost is a critical vulnerability in Grafana’s AI components that uses indirect prompt injection and protocol-relative URL bypasses to exfiltrate data.
AI, Global Security News
GrafanaGhost Exploit Bypasses AI Guardrails for Silent Data Exfiltration
GrafanaGhost chains AI prompt injection and URL flaws to exfiltrate sensitive Grafana data
AI, Apps, Exploits, Global Security News, Network Security, Risk Management
Zero‑click Grafana AI attack can enable enterprise data exfiltration
Indirect prompt injection is possible on AI-powered dashboards, allowing exfiltration of sensitive enterprise data without user authentication. Security researchers are warning about a critical Grafana issue, dubbed GrafanaGhost, that allows attackers to leak sensitive data from Grafana environments, including financial metrics, infrastructure health data, private customer data, and operational logs, among others. Noma Security disclosed…
AI, Apps, Exploits, Global Security News
Google Workspace’s continuous approach to mitigating indirect prompt injections
Posted by Adam Gavish, Google GenAI Security Team Indirect prompt injection (IPI) is an evolving threat vector targeting users of complex AI applications with multiple data sources, such as Workspace with Gemini. This technique enables the attacker to influence the behavior of an LLM by injecting malicious instructions into the data or tools used by…
Endpoint, Exploits, Global Security News
Critical Fortinet FortiClient EMS bug under active attack (CVE-2026-21643)
A critical SQL injection vulnerability (CVE-2026-21643) in Fortinet FortiClient Endpoint Management Server (EMS), a management server for FortiClient endpoint agents on various platforms, is under active exploitation. The warning comes from Defused Cyber, which helps organizations deploy honeypots/fake assets, and uses them as well to capture real attack attempts and exploits and provide early warning…
Global Security News
Critical Flaw in Langflow AI Platform Under Attack
Threats actors pounced on the code injection vulnerability within hours of its disclosure, demonstrating that organizations have little time to address critical bugs.
AI, Apps, Global Security News
Arcjet enables inline defense against prompt injection in production AI systems
Arcjet has released AI Prompt Injection Protection, a new capability designed to stop prompt injection attacks before they reach production AI models. The feature detects hostile prompts at the application boundary and gives developers a decision point inside the request lifecycle where malicious instructions can be blocked before inference occurs. Companies are shipping AI features…
AI, Global Security News, Network Security
‘Claudy Day’ Trio of Flaws Exposes Claude Users to Data Theft
A prompt injection vulnerability paired with other flaws can turn a Google search into a full attack chain that could threaten enterprise networks.
AI, Apps, Cybersecurity, Data Breaches, Endpoint, Exploits, Global Security News, malware, Network Security, Risk Management
AI Risks, Critical Vulnerabilities, and Data Breaches Define This Week in Cybersecurity
Major Threats & Vulnerabilities Critical Software and Platform Flaws A SQL injection flaw in Elementor’s Ally accessibility plugin exposed over 400,000 WordPress sites to potential data theft. The vulnerability stemmed from improper input sanitization, allowing attackers to extract sensitive database information. Administrators should update immediately to the patched version. Microsoft’s March Patch Tuesday addressed a…
AI, Global Security News
SQL Injection Vulnerability in Ally WordPress Plugin Exposes 200K+ Sites
SQL injection flaw in Ally WordPress plugin exposes 200,000+ sites to data theft. Patch released, but most installations remain unpatched and vulnerable.
AI, Exploits, Global Security News, Risk Management
Critical SQL Injection bug in Ally plugin threatens 400,000+ WordPress sites
An unauthenticated SQL injection flaw (CVE-2026-2413) in the Ally WordPress plugin, used on 400K+ sites, could allow attackers to steal sensitive data. An unauthenticated SQL injection flaw, tracked as CVE-2026-2413 (CVSS score 7.5), in Ally plugin could allow attackers to steal sensitive data. The offensive security engineer Drew Webber at Acquia discovered the vulnerability on…
Exploits, Global Security News
SQLi flaw in Elementor Ally plugin impacts 250k+ WordPress sites
An SQL injection vulnerability in Ally, a WordPress plugin from Elementor for web accessibility and usability with more than 400,000 installations, could be exploited to steal sensitive data without authentication. […]
Exploits, Global Security News
VMware Aria Operations Bug Exploited, Cloud Resources at Risk
Exploitation of the command injection flaw in VMware Aria Operations could grant an attacker broad acess to victims’ cloud environments.
AI, Global Security News
How Deepfakes and Injection Attacks Are Breaking Identity Verification
Deepfakes and injection attacks are targeting identity verification moments, from onboarding to account recovery. Incode explains why enterprises must validate the full session—media, device integrity, and behavior—to stop synthetic and injected attacks in real time. […]
Exploits, Global Security News
CISA flags exploited FileZen command injection bug, patch now! (CVE-2026-25108)
CISA has added CVE-2026-25108, an OS command injection vulnerability in Soliton Systems’ FileZen secure file transfer solution, to its Known Exploited Vulnerabilities (KEV) catalog. The vendor has confirmed active exploitation, stating it has received multiple reports of damage caused by attackers abusing the flaw. Because public disclosures from the Japanese CERT Coordination Center (JPCERT/CC) and…