ServicesBlogPricingContactContact Now

Grivyonx Intelligence Hub

Intelligence Hub Archive - Page 63

Older cybersecurity, AI and cloud security analysis from the Grivyonx research team.

AI

AI Sandbox Flaws: Data Theft & RCE Risks Unveiled

A new investigation reveals that popular AI development platforms—Amazon Bedrock, LangSmith, and SGLang—contain sandbox design flaws that can be abused to steal data and launch remote code execution attacks. The findings highlight how DNS queries can become covert channels for exfiltrating sensitive information from AI code‑execution environments. The report, authored by security firm BeyondTrust, demonstrates a practical exploit against Amazon Bedrock's AgentCore interpreter, showing how attackers can gain an interactive shell and move laterally within a target network. These revelations underscore the urgent need for stronger isolation and monitoring in AI‑driven workloads.

By Gourav Rajput

Cyber Security

LeakNet Ransomware Exploits ClickFix Tactics and Deno Loader

LeakNet ransomware has shifted its initial‑access strategy, leveraging the ClickFix social‑engineering technique through compromised websites. By prompting victims to run fabricated commands, the group bypasses traditional credential‑theft methods. The campaign also introduces a Deno‑based in‑memory loader, allowing the malicious payload to execute without touching disk. This combination creates a stealthy, fast‑moving threat that challenges conventional detection tools.

By Gourav Rajput

Cyber Security

CISA Flags Actively Exploited Wing FTP Path Leak Vulnerability

The U.S. Cybersecurity and Infrastructure Security Agency (CISA) has placed the Wing FTP information‑disclosure flaw, CVE‑2025‑47813, into its Known Exploited Vulnerabilities catalog. The medium‑severity issue leaks server installation paths and is already being leveraged by threat actors. Experts recommend immediate mitigation steps, including patching, configuration hardening, and continuous monitoring, to reduce exposure while organizations reassess their reliance on legacy FTP services.

By Gourav Rajput

AI

OpenClaw AI Agent Risks: Vulnerabilities Exposed

A recent advisory from China's National Computer Network Emergency Response Technical Team (CNCERT) has highlighted significant security concerns surrounding the OpenClaw AI agent. The self-hosted, open-source platform, previously known as Clawdbot and Moltbot, presents serious risks due to its default configurations.

By Gourav Rajput

Cyber Security

GlassWorm Exploits VSX Extensions: New Dev Threat

A sophisticated evolution of the GlassWorm campaign has been identified, significantly escalating its reach by exploiting the Open VSX registry. This new tactic weaponizes a large number of extensions to infiltrate developer environments.

By Gourav Rajput

Cyber Security

INTERPOL's Cyber Sweep: 45,000 IPs Down, 94 Arrested

In a significant global operation, INTERPOL has successfully dismantled a vast network of malicious digital infrastructure, taking down 45,000 IP addresses and servers. This coordinated effort also led to the apprehension of 94 individuals suspected of involvement in various cybercriminal activities.

By Gourav Rajput

Cyber Security

Unmasking Click-Fix: A Deep Dive into a New Threat

Cybersecurity researchers have identified a novel iteration of the Click-Fix malware, signaling an alarming evolution in its operational tactics. This new variant poses a significant threat, necessitating a deeper understanding of its mechanisms and potential impact.

By Gourav Rajput

Cyber Security

CrackArmor Flaws: Linux AppArmor Vulnerabilities Uncovered

Security researchers have brought to light a significant set of nine vulnerabilities, collectively dubbed 'CrackArmor,' within the Linux kernel's AppArmor module. These flaws could potentially allow unprivileged users to gain elevated system access and bypass crucial security barriers.

By Gourav Rajput

Cyber Security

Chrome Patches Zero-Days: Skia and V8 Vulnerabilities Addressed

Google has swiftly deployed emergency patches for its widely used Chrome browser, targeting two severe security vulnerabilities that were actively being exploited by malicious actors. These 'zero-day' flaws, meaning they were known and exploited before a fix was available, posed a significant risk to users worldwide.

By Gourav Rajput

AI

AI-Powered Slopoly Malware Fuels Hive0163 Ransomware Attacks

A new frontier in cybercrime is emerging as threat actors increasingly adopt artificial intelligence (AI) to craft sophisticated attack tools. Researchers have uncovered "Slopoly," an AI-assisted malware strain, being utilized by the financially motivated group Hive0163 to gain persistent access during ransomware operations.

By Gourav Rajput

Cyber Security

VENON Malware: Rust's Rise in Brazilian Banking Cybercrime

A new, sophisticated banking malware named VENON has emerged, targeting 33 Brazilian financial institutions. What sets VENON apart is its foundation: it's built using the Rust programming language, a notable shift from the typical Delphi-based tools prevalent in the region's cybercrime landscape.

By Gourav Rajput

Cyber Security

Phishing Attacks: Weaponizing Your SOC's Workload

Phishing attacks are evolving beyond tricking individual employees. Modern campaigns are strategically engineered to overload and exhaust Security Operations Center (SOC) analysts, turning routine investigations into critical vulnerabilities. This shift in attacker methodology poses a significant threat, as prolonged investigation times can escalate minor incidents into major data breaches.

By Gourav Rajput

Cyber Security

Critical n8n Vulnerability Exploited: CISA Issues Warning

The U.S. Cybersecurity and Infrastructure Security Agency (CISA) has added a significant security flaw affecting the n8n workflow automation tool to its actively exploited vulnerabilities list. This critical vulnerability, known as CVE-2025-68613, poses a severe risk due to its potential for remote code execution.

By Gourav Rajput

AI

AI Browsers Vulnerable to Phishing Attacks

The rapid advancement of AI-powered web browsers, designed to autonomously navigate and interact with the internet, has introduced a new frontier in cybersecurity concerns. Recent findings demonstrate that these sophisticated tools, capable of complex reasoning, can be surprisingly susceptible to malicious manipulation, falling victim to phishing schemes within minutes.

By Gourav Rajput

Cyber Security

n8n Vulnerabilities: RCE & Credential Exposure Fixed

Two critical vulnerabilities discovered in the n8n workflow automation platform have been successfully patched. These flaws posed significant risks, including the potential for remote code execution and the exposure of sensitive stored credentials.

By Gourav Rajput

AI

Rust Crates Hijack CI/CD: AI Bots Steal Dev Secrets

Cybersecurity researchers have uncovered a sophisticated attack campaign involving five malicious Rust crates disguised as legitimate time-related utilities. These nefarious packages, published on the official crates.io repository, are designed to infiltrate and compromise Continuous Integration/Continuous Deployment (CI/CD) pipelines, ultimately aiming to exfiltrate sensitive developer secrets.

By Gourav Rajput

AI

LLMs Learn Trust: Enhancing Instruction Hierarchy & Safety

The complexity of Large Language Models (LLMs) presents ongoing challenges in ensuring they follow instructions accurately and safely. A novel approach, the IH-Challenge, is emerging to address this by teaching LLMs to discern and prioritize trusted instructions, thereby enhancing their overall reliability and security.

By Gourav Rajput

Cyber Security

FortiGate Exploits: Attackers Steal Credentials

A concerning new cyber threat has emerged, with malicious actors targeting FortiGate Next-Generation Firewall (NGFW) devices. These attacks leverage vulnerabilities or weak login details to gain unauthorized access, ultimately aiming to pilfer sensitive service account credentials and map out victim networks.

By Gourav Rajput