Tag: injection
-
Measuring Agentic AI Posture: A New Metric for CISOs
In cybersecurity, we live by our metrics. We measure Mean Time to Respond (MTTR), Dwell Time, and Patch Cadence. These numbers indicate to the Board how quickly we respond when issues arise. But in the era of Agentic AI, reaction speed is no longer enough. When an AI Agent or an MCP server is compromised,…
-
Ivanti provides temporary patches for actively exploited EPMM zero-day (CVE-2026-1281)
Ivanti has released provisional patches that fix two critical code injection vulnerabilities in Endpoint Manager Mobile (EPMM), one of which (CVE-2026-1281) has been exploited … First seen on helpnetsecurity.com Jump to article: www.helpnetsecurity.com/2026/01/30/ivanti-epmm-cve-2026-1281-cve-2026-1340/
-
The Agentic AI Posture Score: A New Metric for CISOs
In cybersecurity, we live by our metrics. We measure Mean Time to Respond (MTTR), Dwell Time, and Patch Cadence. These numbers tell the Board how fast we react when things go wrong. But in the era of Agentic AI, reaction speed is no longer enough. When an AI Agent or an MCP server is compromised,…
-
MIND Extends DLP Reach to AI Agents
MIND extends its data loss prevention platform to secure agentic AI, enabling organizations to discover, monitor, and govern AI agents in real time to prevent sensitive data exposure, shadow AI risks, and prompt injection attacks. First seen on securityboulevard.com Jump to article: securityboulevard.com/2026/01/mind-extends-dlp-reach-to-ai-agents/
-
MIND Extends DLP Reach to AI Agents
MIND extends its data loss prevention platform to secure agentic AI, enabling organizations to discover, monitor, and govern AI agents in real time to prevent sensitive data exposure, shadow AI risks, and prompt injection attacks. First seen on securityboulevard.com Jump to article: securityboulevard.com/2026/01/mind-extends-dlp-reach-to-ai-agents/
-
MIND Extends DLP Reach to AI Agents
MIND extends its data loss prevention platform to secure agentic AI, enabling organizations to discover, monitor, and govern AI agents in real time to prevent sensitive data exposure, shadow AI risks, and prompt injection attacks. First seen on securityboulevard.com Jump to article: securityboulevard.com/2026/01/mind-extends-dlp-reach-to-ai-agents/
-
TP-Link Archer Router Flaw Exposes Users to Remote Attacks and Full Device Control
A high command injection vulnerability has been discovered in TP-Link’s Archer MR600 v5 router, enabling authenticated attackers to execute arbitrary system commands through the device’s admin interface. The flaw, tracked as CVE-2025-14756, represents a significant security risk for enterprise and home users relying on this widely deployed network equipment. Vulnerability Details Security researchers identified the…
-
Two High-Severity n8n Flaws Allow Authenticated Remote Code Execution
Cybersecurity researchers have disclosed two new security flaws in the n8n workflow automation platform, including a crucial vulnerability that could result in remote code execution.The weaknesses, discovered by the JFrog Security Research team, are listed below -CVE-2026-1470 (CVSS score: 9.9) – An eval injection vulnerability that could allow an authenticated user to bypass the Expression…
-
APT Attacks Target Indian Government Using GOGITTER, GITSHELLPAD, and GOSHELL – Part 1
Tags: access, adobe, ai, antivirus, api, apt, attack, authentication, backdoor, backup, cloud, control, data, data-breach, detection, email, endpoint, github, google, government, group, india, infection, infrastructure, injection, Internet, malicious, malware, microsoft, network, phishing, service, spear-phishing, threat, tool, update, windowsIntroductionIn September 2025, Zscaler ThreatLabz identified two campaigns, tracked as Gopher Strike and Sheet Attack, by a threat actor that operates in Pakistan and primarily targets entities in the Indian government. In both campaigns, ThreatLabz identified previously undocumented tools, techniques, and procedures (TTPs). While these campaigns share some similarities with the Pakistan-linked Advanced Persistent Threat (APT) group, APT36, we…
-
Breaking Trust with Words: Prompt Injection Leading to Simulated /etc/passwd Disclosure
Tags: injectionFirst seen on resecurity.com Jump to article: www.resecurity.com/blog/article/breaking-trust-with-words-prompt-injection-leading-to-simulated-etcpasswd-disclosure
-
Pwn2Own Automotive 2026: Researchers Score $516,500 For 37 Unique Zero-Days
Day Two of Pwn2Own Automotive 2026 kicked off with high intensity, as security researchers targeted automotive infotainment systems, EV chargers, and gateways. Building on Day One’s momentum, teams demonstrated 37 unique zero-day vulnerabilities, earning over $516,500 in bounties. The Zero Day Initiative (ZDI) event highlights critical flaws in vehicle tech, from command injections to buffer…
-
Critical Vivotek Flaw Enables Remote Arbitrary Code Execution
Tags: ai, botnet, cctv, cve, cyber, flaw, injection, intelligence, iot, reverse-engineering, vulnerabilityAkamai’s Security Intelligence and Response Team (SIRT) uncovered a serious command injection vulnerability in legacy Vivotek IoT camera firmware. Tracked as CVE-2026-22755, the flaw lets remote attackers inject and run arbitrary code as root without authentication. Researchers used AI-driven reverse engineering to find it, confirming impact on dozens of older camera models. This boosts botnet…
-
NVIDIA CUDA Toolkit Flaw Allows Command Injection, Arbitrary Code Execution
NVIDIA has patched critical vulnerabilities in its CUDA Toolkit that expose developers and GPU-accelerated systems to command injection and arbitrary code execution risks. Released on January 20, 2026, the update addresses four flaws in Nsight Systems and related tools, all tied to the CUDA Toolkit ecosystem. Attackers could exploit these via malicious inputs during manual…
-
Node.js binary-parser Library Flaw Enables Malicious Code Injection
A critical code injection vulnerability in the popular Node.js binary-parser library exposes applications to arbitrary JavaScript execution. CERT/CC published Vulnerability Note VU#102648 on January 20, 2026, assigning it CVE-2026-1245. The flaw affects versions before 2.3.0 and stems from unsafe dynamic code generation. Developers using untrusted input for parser definitions face severe risks, including full process…
-
ClearFake malware Exploits Proxy Execution to Run Malicious PowerShell Commands via Trusted Windows Feature
Tags: cyber, detection, endpoint, exploit, injection, malicious, malware, powershell, vulnerability, windowsA sophisticated evolution of the ClearFake malware campaign has emerged, deploying advanced evasion techniques that abuse legitimate Windows components to bypass endpoint detection systems. The operation, which has compromised hundreds of websites since August 2025, now leverages a command injection vulnerability in a trusted Windows script to silently execute malicious PowerShell code, while hosting its…
-
NVIDIA Nsight Graphics on Linux Exposed to Code Execution Vulnerability
NVIDIA has released an urgent security update addressing a critical vulnerability in NSIGHT Graphics for Linux systems. The vulnerability, tracked as CVE-2025-33206, allows attackers to execute arbitrary code through command injection, posing significant risks to development and graphics analysis workflows. Vulnerability Overview The flaw exists in NVIDIA NSIGHT Graphics across all Linux versions prior to…
-
Critical Zoom Vulnerability Enables Remote Code Execution via Command Injection
A critical command injection vulnerability in Zoom Node Multimedia Routers (MMRs) has been disclosed, potentially allowing meeting participants to execute arbitrary code on vulnerable systems. The flaw affects Zoom Node Meetings Hybrid and Meeting Connector deployments, requiring immediate patching across enterprise environments. Vulnerability Overview Zoom Offensive Security identified a command injection flaw in Zoom Node…
-
Three vulnerabilities in Anthropic Git MCP Server could let attackers tamper with LLMs
mcp-server-git versions prior to 2025-12.18.The three vulnerabilities are·CVE-2025-68143, an unrestricted git_init.·CVE-2025-68145, a path validation bypass.·CVE-2025-68144, an argument injection in git_diff.Unlike other vulnerabilities in MCP servers that required specific configurations, these work on any configuration of Anthropic’s official server, out of the box, Cyata says.Model Context Protocol (MCP) is an open standard introduced by Anthropic in 2024 to…
-
Google Gemini Flaw Turns Calendar Invites Into Attack Vector
The indirect prompt injection vulnerability allows an attacker to weaponize calendar invites to circumvent Google’s privacy controls and access private data. First seen on darkreading.com Jump to article: www.darkreading.com/cloud-security/google-gemini-flaw-calendar-invites-attack-vector
-
Prompt Injection Bugs Found in Official Anthropic Git MCP Server
Three vulnerabilities in Anthropic’s Git server for the MCP can be exploited via prompt injection First seen on infosecurity-magazine.com Jump to article: www.infosecurity-magazine.com/news/prompt-injection-bugs-anthropic/
-
Exploiting Google Gemini to Abuse Calendar Invites Illustrates AI Threats
Researchers with security firm Miggo used an indirect prompt injection technique to manipulate Google’s Gemini AI assistant to access and leak private data in Google Calendar events, highlighting the challenges AI presents that traditional security measures can’t address. First seen on securityboulevard.com Jump to article: securityboulevard.com/2026/01/exploiting-google-gemini-to-abuse-calendar-invites-illustrates-ai-threats/
-
Exploiting Google Gemini to Abuse Calendar Invites Illustrates AI Threats
Researchers with security firm Miggo used an indirect prompt injection technique to manipulate Google’s Gemini AI assistant to access and leak private data in Google Calendar events, highlighting the challenges AI presents that traditional security measures can’t address. First seen on securityboulevard.com Jump to article: securityboulevard.com/2026/01/exploiting-google-gemini-to-abuse-calendar-invites-illustrates-ai-threats/
-
Exploiting Google Gemini to Abuse Calendar Invites Illustrates AI Threats
Researchers with security firm Miggo used an indirect prompt injection technique to manipulate Google’s Gemini AI assistant to access and leak private data in Google Calendar events, highlighting the challenges AI presents that traditional security measures can’t address. First seen on securityboulevard.com Jump to article: securityboulevard.com/2026/01/exploiting-google-gemini-to-abuse-calendar-invites-illustrates-ai-threats/
-
Three Flaws in Anthropic MCP Git Server Enable File Access and Code Execution
A set of three security vulnerabilities has been disclosed in mcp-server-git, the official Git Model Context Protocol (MCP) server maintained by Anthropic, that could be exploited to read or delete arbitrary files and execute code under certain conditions.”These flaws can be exploited through prompt injection, meaning an attacker who can influence what an AI assistant…
-
Anthropic quietly fixed flaws in its Git MCP server that allowed for remote code execution
Prompt injection for the win First seen on theregister.com Jump to article: www.theregister.com/2026/01/20/anthropic_prompt_injection_flaws/
-
Google Gemini flaw exposes new AI prompt injection risks for enterprises
Real enterprise exposure: Analysts point out that the risk is significant in enterprise environments as organizations rapidly deploy AI copilots connected to sensitive systems.”As internal copilots ingest data from emails, calendars, documents, and collaboration tools, a single compromised account or phishing email can quietly embed malicious instructions,” said Chandrasekhar Bilugu, CTO of SureShield. “When employees…
-
OverAir Software Updates Pose Risks to Vehicles
eSync Alliance Chair Shrikant Acharya on How Standardization Can Prevent Breaches. Over-the-air updates are an irreplaceable part of software-defined vehicles, giving manufacturers a convenient way of remotely fixing and upgrading vehicles. If not appropriately secured, over-the-air updates can become a gateway for data theft, malware injection, vehicle theft and even injury. First seen on govinfosecurity.com…
-
Google Gemini Prompt Injection Flaw Exposed Private Calendar Data via Malicious Invites
Tags: control, cybersecurity, data, data-breach, flaw, google, injection, malicious, privacy, vulnerabilityCybersecurity researchers have disclosed details of a security flaw that leverages indirect prompt injection targeting Google Gemini as a way to bypass authorization guardrails and use Google Calendar as a data extraction mechanism.The vulnerability, Miggo Security’s Head of Research, Liad Eliyahu, said, made it possible to circumvent Google Calendar’s privacy controls by hiding a dormant…
-
Five Chrome extensions caught hijacking enterprise sessions
Blocking defenses and hijacking sessions: The campaign went beyond stealing credentials. Two of the extensions, Tool Access 11 and Data By Cloud 2, incorporated DOM manipulation routines that actively blocked access to security and administrative pages within the targeted platforms. This prevented the enterprise admins from reaching screens to change passwords, view sign-on history, or…