Tag: injection
-
Sitecore zero-day configuration flaw under active exploitation
__VIEWSTATE and can be signed and encrypted with keys, called ValidationKey and DecryptionKey, stored in the application configuration file.If these keys are stolen or leaked, attackers can use them to craft malicious ViewState payloads inside POST requests that the server will then decrypt, validate, and execute by loading them into the memory of its worker…
-
Django Web Vulnerability Exposes Applications to High-Risk SQL Injection CVE-2025-57833
A serious Django web vulnerability has been identified, prompting immediate action from the Django web framework development team. The flaw, officially registered as CVE-2025-57833, affects the FilteredRelation feature in Django and could allow attackers to carry out SQL injection attacks. This vulnerability has been marked as high severity, and users of affected versions are urged…
-
Django Web Vulnerability Allows Attackers to Execute SQL Injection
The Django development team has issued security updates after discovering ahigh-severity SQL injection flawin the FilteredRelation feature. This flaw could allow attackers to run harmful database commands by crafting unexpected query parameters. Users running Django 5.2, 5.1, or 4.2 should upgrade immediately to protect their applications. Web Vulnerability Details Django’s FilteredRelation feature helps developers write…
-
Indirect Prompt Injection Attacks Against LLM Assistants
Tags: attack, automation, control, data, disinformation, email, framework, google, injection, LLM, malicious, mitigation, mobile, phishing, risk, risk-assessment, threat, toolReally good research on practical attacks against LLM agents. “Invitation Is All You Need! Promptware Attacks Against LLM-Powered Assistants in Production Are Practical and Dangerous” Abstract: The growing integration of LLMs into applications has introduced new security risks, notably known as Promptware”, maliciously engineered prompts designed to manipulate LLMs to compromise the CIA triad of…
-
Prompt Injection Attacks Can Exploit AI-Powered Cybersecurity Tools
Researchers have demonstrated that advanced prompt injection techniques can turn defensive AI agents into potent vectors for system compromise. The findings, detailed in a new preprint titled “Cybersecurity AI: Hacking the AI Hackers via Prompt Injection,” expose a fundamental architectural weakness in large language model (LLM)based security tools that could upend trust in automated pen-testing…
-
High-Risk SQLi Flaw Exposes WordPress Memberships Plugin Users
A vulnerability in the WordPress Paid Memberships Subscription plugin could lead to unauthenticated SQL injection on affected sites First seen on infosecurity-magazine.com Jump to article: www.infosecurity-magazine.com/news/sqli-threat-wordpress-memberships/
-
Authenticated Attackers Could Exploit IBM Watsonx Vulnerability to Access Sensitive Data
A newly disclosed security vulnerability, tracked as CVE-2025-0165, has been reported, specifically concerning the users of the IBM Watsonx Orchestrate Cartridge within the IBM Cloud Pak for Data platform. The flaw, officially acknowledged in a security bulletin released by IBM on August 31, 2025, enables blind SQL injection attacks, potentially allowing authenticated attackers to manipulate…
-
KI als Cybercrime-Copilot
Tags: ai, business, ciso, cyberattack, cybercrime, dns, group, injection, intelligence, malware, openai, ransomware, RedTeam, sans, strategy, threat, toolDas KI-gestützte Entwickler-Tool Claude Code hat einem Cyberkriminellen dabei geholfen, in Netzwerke einzudringen.CISOs und Sicherheitsentscheider rechnen schon seit längerem damit, dass Cyberangriffe nicht mehr von Menschen mit KI-Tools, sondern von KI-Systemen selbst ausgehen. Diese Befürchtung hat sich nun mit neuen Forschungserkenntnissen bestätigt. So offenbart Anthropics aktueller Threat Intelligence Report , dass das KI-gestützte Entwickler-Tool Claude…
-
KI als Cybercrime-Copilot
Tags: ai, business, ciso, cyberattack, cybercrime, dns, group, injection, intelligence, malware, openai, ransomware, RedTeam, sans, strategy, threat, toolDas KI-gestützte Entwickler-Tool Claude Code hat einem Cyberkriminellen dabei geholfen, in Netzwerke einzudringen.CISOs und Sicherheitsentscheider rechnen schon seit längerem damit, dass Cyberangriffe nicht mehr von Menschen mit KI-Tools, sondern von KI-Systemen selbst ausgehen. Diese Befürchtung hat sich nun mit neuen Forschungserkenntnissen bestätigt. So offenbart Anthropics aktueller Threat Intelligence Report , dass das KI-gestützte Entwickler-Tool Claude…
-
Frequently Asked Questions About Chinese State-Sponsored Actors Compromising Global Networks
Tags: access, advisory, attack, authentication, china, cisa, cisco, credentials, cve, cyber, cybersecurity, data, espionage, exploit, firewall, fortinet, germany, government, identity, infrastructure, injection, ivanti, kev, malicious, microsoft, military, mitigation, mitre, network, remote-code-execution, risk, software, tactics, threat, update, vulnerability, zero-dayAn analysis of Tenable telemetry data shows that the vulnerabilities being exploited by Chinese state-sponsored actors remain unremediated on a considerable number of devices, posing major risk to the organizations that have yet to successfully address these flaws. Background Tenable’s Research Special Operations (RSO) team has compiled this blog to answer Frequently Asked Questions (FAQ)…
-
KI greift erstmals autonom an
Tags: ai, business, ciso, cyberattack, cybercrime, dns, group, injection, intelligence, malware, openai, ransomware, RedTeam, sans, strategy, threat, toolDas KI-gestützte Entwickler-Tool Claude Code hat einem Cyberkriminellen dabei geholfen, in Netzwerke einzudringen.CISOs und Sicherheitsentscheider rechnen schon seit längerem damit, dass Cyberangriffe nicht mehr von Menschen mit KI-Tools, sondern von KI-Systemen selbst ausgehen. Diese Befürchtung hat sich nun mit neuen Forschungserkenntnissen bestätigt. So offenbart Anthropics aktueller Threat Intelligence Report , dass das KI-gestützte Entwickler-Tool Claude…
-
Cisco UCS Manager Software Flaw Allows Attackers to Inject Malicious Commands
Cisco has released urgent security updates to remediate two medium-severity command injection vulnerabilities in its UCS Manager Software that could allow authenticated administrators to execute arbitrary commands and compromise system integrity. Disclosed on August 27, 2025, the advisory (cisco-sa-ucs-multi-cmdinj-E4Ukjyrz) affects multiple UCS fabric interconnect platforms and underscores the importance of timely patching to prevent potential…
-
Anthropic detects the inevitable: genAI-only attacks, no humans involved
Tags: ai, attack, business, ciso, control, cybercrime, cybersecurity, defense, dns, infrastructure, injection, intelligence, malicious, malware, open-source, openai, RedTeam, threat, tool, warfarenot find.”There is potentially a lot of this activity we’re not seeing. Anthropic being open about their platform being used for malicious activities is significant, and OpenAI has recently shared the same as well. But will others open up about what is already likely happening?” Brunkard asked. “Or maybe they haven’t shared because they don’t…
-
We Are Still Unable to Secure LLMs from Malicious Inputs
Nice indirect prompt injection attack: Bargury’s attack starts with a poisoned document, which is shared to a potential victim’s Google Drive. (Bargury says a victim could have also uploaded a compromised file to their own account.) It looks like an official document on company meeting policies. But inside the document, Bargury hid a 300-word malicious…
-
NVIDIA NeMo AI Curator Vulnerability Allows Code Execution and Privilege Escalation
NVIDIA released a security bulletin for NVIDIA® NeMo Curator addressing a high-severity vulnerability (CVE-2025-23307) that affects all prior versions of the Curator software. The flaw, rooted in improper handling of user-supplied files, allows a maliciously crafted file to be processed by NeMo Curator, leading to code injection and arbitrary code execution. Successful exploitation can result…
-
AI Security Map: Linking AI vulnerabilities to real-world impact
A single prompt injection in a customer-facing chatbot can leak sensitive data, damage trust, and draw regulatory scrutiny in hours. The technical breach is only the first … First seen on helpnetsecurity.com Jump to article: www.helpnetsecurity.com/2025/08/27/ai-security-map-linking-vulnerabilities-real-world-impact/
-
Researchers flag code that uses AI systems to carry out ransomware attacks
The malware, called PromptLock, essentially functions as a hard-coded prompt injection attack on a large language model, inspecting local filesystems, exfiltrating files and encrypting data. First seen on cyberscoop.com Jump to article: cyberscoop.com/prompt-lock-eset-ransomware-research-ai-powered-prompt-injection/
-
The Role of AI Pentesting in Securing LLM Applications
The rapid adoption of Large Language Models (LLMs) has reshaped the digital ecosystem, powering everything from customer service chatbots to advanced data analysis systems. But with this growth comes a wave of new security challenges. Traditional application vulnerabilities still exist, but LLM applications introduce risks such as prompt injection, data poisoning, model leakage, and misuse……
-
The Role of AI Pentesting in Securing LLM Applications
The rapid adoption of Large Language Models (LLMs) has reshaped the digital ecosystem, powering everything from customer service chatbots to advanced data analysis systems. But with this growth comes a wave of new security challenges. Traditional application vulnerabilities still exist, but LLM applications introduce risks such as prompt injection, data poisoning, model leakage, and misuse……
-
The Role of AI Pentesting in Securing LLM Applications
The rapid adoption of Large Language Models (LLMs) has reshaped the digital ecosystem, powering everything from customer service chatbots to advanced data analysis systems. But with this growth comes a wave of new security challenges. Traditional application vulnerabilities still exist, but LLM applications introduce risks such as prompt injection, data poisoning, model leakage, and misuse……
-
Perplexity Comet Browser Prompt Injection als großes Sicherheitsrisiko
Nächster Fail aus dem Bereich KI-Agenten. Die Entwickler des Browse-Browser haben eine Schwachstelle im Perplexity Comet Browser offen gelegt. Per Prompt Injection wäre es möglich, sensitive Informationen aus dem Agenten abzurufen und dem Agenten Anweisungen zu geben, im Namen des … First seen on borncity.com Jump to article: www.borncity.com/blog/2025/08/25/perplexity-comet-browser-prompt-injection-als-sicherheitsrisiko/
-
Rowhammer attack can backdoor AI models with one devastating bit flip
Servers with DDR3 memory modules (demonstrated on 16GB Samsung DDR3)Workstations with DDR4 memory (demonstrated on 8GB Hynix DDR4)AI inference servers running popular models such as ResNet, VGG, and Vision TransformersEdge computing devices with vulnerable DRAM hosting neural networksCloud platforms using DDR3/DDR4 memory for AI model deploymentResearch computing systems running full-precision (32-bit floating-point) modelsMulti-tenant GPU servers…
-
AI Models Resize Photos and Open Door to Hacking
Researchers Show How AI Image Downscaling Can be an Attack Vector. Researchers discovered a method to embed invisible prompt injections that are activated during AI’s processing of an image. When the model scales down these images, the hidden malicious instructions allow theft of data from popular image production systems. First seen on govinfosecurity.com Jump to…
-
Honey, I shrunk the image and now I’m pwned
Google’s Gemini-powered tools tripped up by image-scaling prompt injection First seen on theregister.com Jump to article: www.theregister.com/2025/08/21/google_gemini_image_scaling_attack/
-
Copilot Kept Access Logs Unless You Told It Not To
Copilot Falls for Prompt Injection Yet Again. Microsoft quietly fixed a flaw that allowed users to instruct embedded artificial intelligence model Copilot not to log its access corporate files. If you work at an organization that used Copilot prior to Aug 18, there is a very real chance that your audit log is incomplete. First…