Tag: injection
-
Critical GiveWP Flaw Lets Attackers Run Commands on WordPress Servers
A critical GiveWP flaw lets unauthenticated attackers execute server commands. Version 4.16.7.2 fixes the PHP object injection chain. A critical vulnerability in GiveWP, one of the most widely used WordPress plugins for online donations and fundraising, can let an unauthenticated attacker execute commands on the server. Patchstack disclosed the flaw on August 28, after researcher…
-
Attackers Exploit MCP RCE, Blind Prompt Injection and Memory Credential Theft Against AI Infrastructure
Tags: ai, cloud, credentials, cyber, data-breach, exploit, framework, infrastructure, injection, rce, remote-code-execution, service, theftAttackers are increasingly treating AI infrastructure as a high-value cloud entry point, exploiting exposed Model Context Protocol (MCP) services, agent frameworks, and AI gateways to execute code, validate prompt injection, deploy cryptominers, and steal credentials from process memory. The campaigns show that attackers are no longer using only generic web-server tradecraft; they are tailoring reconnaissance,…
-
ServiceNow Patches Critical Flaws Enabling Unauthenticated RCE and SQL Injection
ServiceNow has issued security advisories for four vulnerabilities, including critical flaws in its AI platform. These vulnerabilities could allow unauthenticated attackers to execute arbitrary code, manipulate instance data, elevate privileges, or run SQL commands against underlying databases. On August 27, 2026, the company published KB3152242, which covers CVE-2026-6876, CVE-2026-18885, CVE-2026-18886, and CVE-2026-74820. ServiceNow reported that…
-
ServiceNow warns of three max severity security vulnerabilities
ServiceNow released security patches for three new maximum-severity AI Platform vulnerabilities that can be exploited in code injection, SQL injection, and privilege escalation attacks. First seen on bleepingcomputer.com Jump to article: www.bleepingcomputer.com/news/security/servicenow-warns-of-three-max-severity-security-vulnerabilities/
-
Prompt Injection Attack Hijacks Claude Code Opus 5 Auto Mode to Execute Malicious Code
A recent demonstration of prompt-injection research has revealed that Claude Code Opus 5, when running in its default Auto Mode, can be manipulated to execute malicious code via a seemingly harmless website summary request. Security researcher Johann Rehberger, who writes under the name >>wunderwuzzi<< at Embrace The Red, reported success rates of 60% to 80%…
-
Amazon Kiro Prompt Injection Can Exfiltrate Sensitive Data Through Kiro Powers
Cybersecurity researchers have disclosed details of a vulnerability in Amazon Kiro, an artificial intelligence (AI)-powered, agentic integrated development environment (IDE), that could facilitate data exfiltration via prompt injection and Kiro Powers.The security flaw, which does not have a CVE identifier, works against Kiro IDE 0.7.45 on Windows, according to Mindguard. The latest version of First…
-
Ubiquiti Fixes 22 UniFi Flaws Enabling Command Injection, Authentication Bypass and Privilege Escalation
Ubiquiti has released security updates to address 22 vulnerabilities across its UniFi ecosystem. These updates include multiple critical flaws that could allow unauthenticated command injection, authentication bypass, and privilege escalation on exposed devices. Documented in Security Advisory Bulletin 067 and published on August 26, 2026, these vulnerabilities affect several components, including UniFi OS, UniFi Protect,…
-
SQL Injection – Google patcht unberechtigte Datenbankabfrage in SecOps
First seen on security-insider.de Jump to article: www.security-insider.de/google-secops-sql-injection-widget-api-patch-6-3-85-a-ff2d16a93654268ef29c026ddcea576f/
-
Stop Building a 2003 SOC with AI: Local Context, Failure Modes and Your Path (Part 3)
In Part 1 of this series, we dumped a pile of uncomfortable questions on you and promised answers. In Part 2 of the series, we talked about why 1990s-2000s alert triage must die. The core thesis, if you recall: if you add AI agents into a legacy, swivel-chair SOC structure, you are essentially building a robotic…
-
Critical Gitea vulnerability now exploited in the wild (CVE-2026-60004)
Attackers have begun exploiting CVE-2026-60004, a critical code injection vulnerability in the Gitea Git platform, CISA confirmed on Tuesday by adding the vulnerability to its … First seen on helpnetsecurity.com Jump to article: www.helpnetsecurity.com/2026/08/26/gitea-cve-2026-60004-exploited-in-the-wild/
-
Hackers now exploit critical Gitea flaw in code injection attacks
Tags: attack, cybersecurity, exploit, flaw, hacker, infrastructure, injection, service, vulnerabilityAttackers are now exploiting a critical-severity vulnerability in the Gitea self-hosted Git service, according to the U.S. Cybersecurity and Infrastructure Security Agency (CISA). First seen on bleepingcomputer.com Jump to article: www.bleepingcomputer.com/news/security/hackers-now-exploit-critical-gitea-flaw-in-code-injection-attacks/
-
Router-Modell DWR-M961 Link patcht kritische Command Injection
First seen on security-insider.de Jump to article: www.security-insider.de/d-link-dwr-m961-15-sicherheitsluecken-root-command-injection-a-2d8b3d1f7d18d7ecdbc347a22880d962/
-
Agentic AI Security: Credentials and Permissions Define the Blast Radius
Prompt injection can’t be patched away. Three 2026 agentic AI incidents show that credentials and permissions decide the damage. First seen on securityboulevard.com Jump to article: securityboulevard.com/2026/08/agentic-ai-security-credentials-and-permissions-define-the-blast-radius/
-
Grok fooled into stealing user chat, location data, and more
Researchers found that prompt injection attacks can hide malicious instructions in encrypted text to get them past AI guardrails. First seen on securityboulevard.com Jump to article: securityboulevard.com/2026/08/grok-fooled-into-stealing-user-chat-location-data-and-more/
-
Grok fooled into stealing user chat, location data, and more
Researchers found that prompt injection attacks can hide malicious instructions in encrypted text to get them past AI guardrails. First seen on securityboulevard.com Jump to article: securityboulevard.com/2026/08/grok-fooled-into-stealing-user-chat-location-data-and-more/
-
TP-Link Archer Command Injection Flaws Enable Root-Level Code Execution
TP-Link has released firmware updates for three Archer router models due to the discovery of multiple command injection vulnerabilities. These vulnerabilities could enable attackers to execute arbitrary operating system commands with root privileges. The security advisory, updated on August 24, 2026, pertains to the Archer BE800 V1, Archer BE3600 V1, and Archer AX75 V1 devices.…
-
Does AI Create New Cybersecurity Risks? What Actually Changes
<div cla AI does not create new attack vectors. It accelerates the ones that already dominate most risk registers. Code exploitation, injection, credential and identity abuse, phishing, and misconfiguration are the same vectors security teams tracked before generative AI reached the enterprise. What changed is how quickly they can be found and exploited, and the…
-
Does AI Create New Cybersecurity Risks? What Actually Changes
<div cla AI does not create new attack vectors. It accelerates the ones that already dominate most risk registers. Code exploitation, injection, credential and identity abuse, phishing, and misconfiguration are the same vectors security teams tracked before generative AI reached the enterprise. What changed is how quickly they can be found and exploited, and the…
-
Zimbra Collaboration Suite Flaw Actively Exploited to Execute Arbitrary Commands
Threat actors are actively exploiting a critical operating system command injection vulnerability in Zimbra Collaboration Suite, identified as CVE-2026-73570. This vulnerability allows unauthenticated attackers to execute arbitrary operating system commands with the privileges of the zimbra user. Zimbra Collaboration Suite Flaw The flaw specifically affects Zimbra deployments where the SNMP trap notification service is enabled…
-
Zimbra Collaboration Suite Flaw Actively Exploited to Execute Arbitrary Commands
Threat actors are actively exploiting a critical operating system command injection vulnerability in Zimbra Collaboration Suite, identified as CVE-2026-73570. This vulnerability allows unauthenticated attackers to execute arbitrary operating system commands with the privileges of the zimbra user. Zimbra Collaboration Suite Flaw The flaw specifically affects Zimbra deployments where the SNMP trap notification service is enabled…
-
Neue Angriffstechnik soll Grok-Chatverläufe über präparierte Webseiten abgreifen
Adversa AI zeigt, wie sich Grok über verschlüsselte Prompt-Injection zum heimlichen Abfluss privater Chatdaten bringen lässt. First seen on it-daily.net Jump to article: www.it-daily.net/it-sicherheit/cybercrime/angriffstechnik-grok
-
Zero-Click Grok Chat History Theft: Adversa AI Demonstrates Cryptographic Context Injection
New Cryptographic Context Injection technique bypasses AI guardrails via AES-encrypted payloads, leaking full Grok chat histories zero-click Adversa AI researcher Rony Utevsky devised a new attack technique, called Cryptographic Context Injection, that bypasses AI safety filters by sending instructions as AES-encrypted ciphertext and tricking the model into decrypting them inside its own code execution runtime.…
-
Zero-Click Grok Attack Lets Hackers Steal Chat History Using Encrypted Prompt Injection
A newly disclosed prompt-injection technique could turn a routine request to summarize a webpage in xAI’s Grok web chat into a silent data-exfiltration attack, potentially exposing a user’s name, approximate location, subscription tier, and active conversation history. Security researchers at Adversa AI have dubbed the technique >>Cryptographic Context Injection.<< The attack targets Grok's ability to…
-
91 Spring CVEs: The AI Vulnerability Consumption Problem
Tags: access, advisory, ai, attack, cloud, cve, cvss, data, data-breach, framework, guide, injection, intelligence, open-source, risk, service, software, tool, update, vulnerability<div cla TL;DR Broadcom released a large batch of Spring security advisories on August 20, 2026, with Sonatype tracking 91 CVEs across Spring Framework and related projects. At the time of publishing, Sonatype Guide currently identifies 209,569 software components affected by the security event. The disclosure comes amid a dramatic rise in AI-assisted vulnerability discovery. Broadcom…
-
GitLab CVE-2026-19478 Comes Under Active Exploitation Within Days of Disclosure
A newly disclosed security flaw in GitLab has come under active exploitation within days of public disclosure, according to watchTowr.The vulnerability in question is CVE-2026-19478 (CVSS score: 9.4), a case of code injection that allows an unauthenticated attacker to modify or delete publicly accessible GitLab projects and rewrite their data under certain conditions without requiring…
-
New Cryptographic Context Injection Attack Could Let Web Pages Steal Grok Chat Data
Adversa AI has disclosed an attack technique that it says can cause xAI’s Grok chatbot to send a user’s name, approximate location, subscription tier, and the prompts from the ongoing conversation to an attacker-controlled server after the user asks it to summarize an ordinary web page.The AI security company, which has codenamed the technique “Cryptographic…
-
Attackers Exploit Zimbra SNMP Flaw for Unauthenticated Remote Code Execution
A now-patched security flaw impacting Zimbra Collaboration (ZCS) has come under active exploitation in the wild, according to the Polish Computer Emergency Response Team (CERT Polska).The vulnerability in question is CVE-2026-73570 (CVSS score: 8.9), which refers to a case of command injection that can lead to remote code execution.”A remote code execution vulnerability exists in…
-
Grok exfiltrates user data when malicious instructions are encrypted
Cryptographic Context Injection is only the latest way to break an LLM safety guardrail. First seen on arstechnica.com Jump to article: arstechnica.com/security/2026/08/grok-exfiltrates-user-data-when-malicious-instructions-are-encrypted/
-
New CRLF Desync Attack Lets Hackers Steal HTTPOnly Cookies and Hijack Accounts
Security researchers Tom Stacey from PortSwigger and Tobia Righi from TurtleSec have introduced a new category of HTTP request smuggling attacks known as >>CRLF-Powered Desync Attacks.<< This method exploits a frequently overlooked HTTP header injection vulnerability, which can lead to full account takeovers, theft of HTTPOnly cookies, and even the creation of self-propagating desync worms.…
-
Cisco BroadWorks Vulnerability Allows Remote Attackers to Access Sensitive Files
Cisco has issued security updates for a high-severity vulnerability in Cisco BroadWorks that could allow unauthenticated remote attackers to access sensitive configuration files on affected systems. This vulnerability is tracked as CVE-2026-20320 and is characterized as an out-of-band blind XML External Entity (XXE) injection vulnerability in the Open Client Interface (OCI) XML Parser. Cisco assigned…