Artificial Intelligence — Cybersecurity News

Most Popular News

Top stories by views
Hackers Exploit CVE-2025-55182 to Breach 766 Next.js Hosts, Steal Credentials
1,591 views
CVE category

Hackers Exploit CVE-2025-55182 to Breach 766 Next.js Hosts, Steal Credentials

RedSide Security April 04, 2026
Read: Hackers Exploit CVE-2025-55182 to Breach…
Passwd: A walkthrough of the Google Workspace Password Manager
472 views

Passwd: A walkthrough of the Google Workspace Password Manager

Dec 26, 2025
Top 10 High-Risk Vulnerabilities Of 2025 that Exploited in the Wild
462 views

Top 10 High-Risk Vulnerabilities Of 2025 that Exploited in the Wild

Jan 02, 2026
Google Patches Actively Exploited Chrome Zero-Day (CVE-2026-2441)
458 views

Google Patches Actively Exploited Chrome Zero-Day (CVE-2026-2441)

Feb 17, 2026
OpenAI Hardened ChatGPT Atlas Against Prompt Injection Attacks
443 views

OpenAI Hardened ChatGPT Atlas Against Prompt Injection Attacks

Dec 29, 2025
PCAPGraph: Threat Hunting at the Speed of Triage

PCAPGraph: Threat Hunting at the Speed of Triage

PCAPGraph is an open-source network investigation and threat hunting tool that transforms packet cap...

June 04, 2026
Open-Source Network Discovery & Topology Mapping

Open-Source Network Discovery & Topology Mapping

RedSide Security has open-sourced NETMAPPER, a network discovery and visualization tool designed to ...

June 03, 2026
RDPGraph: Turn Windows Event Logs into an Interactive RDP Attack Graph

RDPGraph: Turn Windows Event Logs into an Interactive RDP Attack Graph

When an incident unfolds and all you have left are Windows event logs, understanding attacker moveme...

June 03, 2026

Latest Posts

Encrypted AI Reasoning Traces Can Leak Secrets Across API Sessions

Encrypted AI Reasoning Traces Can Leak Secrets Across API Sessions

RedSide Security August 12, 2026 AI Security 61 views

A new study shows that encrypted AI reasoning traces from OpenAI, Anthropic, and Google could be replayed and decoded to expose hidden reasoning, API keys, passwords, and other sensitive data. Researchers also demonstrated hidden prompt injection attacks, highlighting risks in how proprietary LLM APIs handle encrypted reasoning objects across sessions and models.

Cybersecurity Prompt Injection Threat Intelligence AI Security OpenAI Artificial Intelligence API Security LLM Security Google Gemini Credential Theft Anthropic AI Reasoning Reasoning Traces Data Leakage Model Security
Continue reading: Encrypted AI Reasoning Traces Can Leak Secrets Acr…
Anthropic Reveals Claude AI Compromised Three Real Organizations During Cybersecurity Evaluations

Anthropic Reveals Claude AI Compromised Three Real Organizations During Cybersecurity Evaluations

RedSide Security July 31, 2026 Cybersecurity 72 views

Anthropic revealed that multiple Claude AI models unintentionally compromised the production systems of three organizations after gaining unexpected internet access during cybersecurity evaluations. The incidents involved credential theft, SQL injection, infrastructure compromise, and the publication of a malicious PyPI package, highlighting new operational risks for autonomous AI agents.

Cybersecurity AI Information Security Incident Response Security Research Threat Intelligence Artificial Intelligence Technology Anthropic Claude AI
Continue reading: Anthropic Reveals Claude AI Compromised Three Rea…
Researchers Find 282 iPhone AI Apps Exposing Paid AI Access Through Leaked API Credentials

Researchers Find 282 iPhone AI Apps Exposing Paid AI Access Through Leaked API Credentials

RedSide Security June 30, 2026 Vulnerability 77 views

Researchers analyzing 444 AI chatbot apps on iPhone found that 282 applications exposed paid AI access through leaked API keys, reusable tokens, or unsecured backend services. The findings highlight growing risks of LLMJacking attacks, where threat actors abuse stolen AI credentials to generate costly unauthorized model usage.

Information Security AI Security Cloud Security OpenAI Artificial Intelligence API Security API Keys LLM Security LLMJacking Google Gemini Mobile Security iOS Security Application Security Data Exposure Credential Leakage Token Security App Store Security Wake Forest University Cybersecurity Research AI Applications
Continue reading: Researchers Find 282 iPhone AI Apps Exposing Paid …
GuardFall Bypass Lets Attackers Evade AI Coding Agent Safety Checks Using Decades-Old Shell Tricks

GuardFall Bypass Lets Attackers Evade AI Coding Agent Safety Checks Using Decades-Old Shell Tricks

RedSide Security June 30, 2026 Cybersecurity 105 views

Researchers have disclosed GuardFall, a shell command bypass technique that defeats safety protections in 10 popular AI coding agents. The flaw allows malicious commands to evade text-based filters and execute with user privileges, potentially exposing credentials, source code, and cloud infrastructure.

Cybersecurity Prompt Injection Linux Security Security Research Open Source Security AI Security Cloud Security Artificial Intelligence AI Agents Coding Agents GuardFall Adversa AI Command Injection Bash Security DevSecOps Secure Coding GitHub CI/CD Security Threat Research Software Supply Chain Security
Continue reading: GuardFall Bypass Lets Attackers Evade AI Coding Ag…