Skip to main content
← All Articles

Tag

#AI Security

277 articles

Advertisement

INFO
Compliance

G7 Hiroshima AI Process Releases AI SBOM Transparency Guidance

New G7 guidance establishes minimum requirements for AI Software Bill of Materials to improve transparency and security within the global AI supply chain.

Runtime Rebel Intel
3 min read · May 14, 2026
PraisonAI Auth Bypass CVE-2026-44338 Exploited — Patching Guide
HIGH
Vulnerabilities

PraisonAI Auth Bypass CVE-2026-44338 Exploited — Patching Guide

Threat actors are actively exploiting CVE-2026-44338, a critical authentication bypass in the PraisonAI framework, just hours after public disclosure.

Runtime Rebel Intel
4 min read · May 14, 2026
Microsoft MDASH AI Discovers 16 Windows Vulnerabilities
HIGH
Vulnerabilities

Microsoft MDASH AI Discovers 16 Windows Vulnerabilities

Microsoft reveals MDASH, a new AI-driven agentic scanning harness that discovered 16 vulnerabilities in Windows, now fixed in recent Patch Tuesday updates.

Runtime Rebel Intel
3 min read · May 13, 2026
MEDIUM
Threat Intel

GPT-5.5 Performance in Automated Vulnerability Discovery

An analysis of GPT-5.5 and Claude Mythos capabilities in identifying security vulnerabilities based on UK AI Security Institute evaluations.

Runtime Rebel Intel
3 min read · May 13, 2026
HIGH
Vulnerabilities

May 2026 Patch Tuesday: AI-Driven Bug Discovery Scales Patch Volumes

Software vendors report record security fixes for May 2026 as AI tools accelerate vulnerability discovery. Analyze the impact on enterprise patch management.

Runtime Rebel Intel
3 min read · May 13, 2026
Hugging Face Model Supply Chain Vulnerability: Tokenizer Hijacking
HIGH
Supply Chain

Hugging Face Model Supply Chain Vulnerability: Tokenizer Hijacking

Attackers can weaponize Hugging Face AI models by manipulating tokenizer files, leading to model output hijacking and sensitive data exfiltration.

Runtime Rebel Intel
4 min read · May 12, 2026

Advertisement

HIGH
Threat Intel

AI-Augmented Zero-Day Exploitation and Autonomous Malware Orchestration

GTIG report reveals how threat actors leverage generative AI for zero-day discovery, autonomous Android malware orchestration, and AI supply chain attacks.

Runtime Rebel Intel
4 min read · May 11, 2026
INFO
Threat Intel

LLM Text-in-Text Steganography: Emerging Covert Channel Risks

Analysis of how Large Language Models enable sophisticated text-in-text steganography for covert communication, data exfiltration, and C2 operations.

Runtime Rebel Intel
4 min read · May 11, 2026
CVE-2026-7482: Bleeding Llama Memory Leak in Ollama — Patch Now
HIGH
Vulnerabilities

CVE-2026-7482: Bleeding Llama Memory Leak in Ollama — Patch Now

Remote attackers can exploit CVE-2026-7482 in Ollama to leak process memory. Protect your AI infrastructure from the Bleeding Llama vulnerability impact.

Runtime Rebel Intel
3 min read · May 10, 2026
INFO
Threat Intel

AI-Driven SOC Workflows: Why Scaling Analysts Fails to Solve Alert Fatigue

Examine why hiring more analysts cannot solve SOC alert fatigue and how AI-driven threat investigation workflows are necessary to reduce MTTR effectively.

Runtime Rebel Intel
3 min read · May 8, 2026
HIGH
Data Breach

Braintrust AWS Breach: Immediate AI Provider API Key Rotation Required

Braintrust prompts users to rotate API keys after unauthorized AWS account access compromised AI provider secrets. Learn about the impact and mitigation.

Runtime Rebel Intel
3 min read · May 8, 2026
AI CLI Tools Vulnerable to RCE via Malicious Repositories
HIGH
Threat Intel

AI CLI Tools Vulnerable to RCE via Malicious Repositories

TrustFall research reveals RCE risks in Claude Code and Cursor CLI. AI agents can be manipulated via malicious repositories to execute arbitrary commands.

Runtime Rebel Intel
4 min read · May 7, 2026
INFO
Threat Intel

AI Red Teaming: Guardrail Manipulation via Jailbreaking and Data Poisoning

Explores AI red teaming methods like jailbreaking and data poisoning used to manipulate AI guardrails and harden machine learning models against adversarial attacks.

Runtime Rebel Intel
4 min read · May 6, 2026
Insecure Self-Hosted AI: 1 Million Exposed Services Risks Analyzed
HIGH
Cloud Security

Insecure Self-Hosted AI: 1 Million Exposed Services Risks Analyzed

A security scan of 1 million exposed AI services reveals critical vulnerabilities in self-hosted LLM infrastructure and misconfigured model deployments.

Runtime Rebel Intel
3 min read · May 5, 2026
INFO
Identity & Access

Cisco Acquires Astrix: Tackling Non-Human Identity Risks for AI & Machines

Cisco's acquisition of Astrix Security targets emerging non-human identity risks in AI and machine access, enhancing identity-centric security for cloud environments.

Runtime Rebel Intel
5 min read · May 4, 2026
INFO
Vulnerabilities

Google Adjusts Bug Bounties: $1.5M Android Reward and AI Shift

Google updates its Vulnerability Reward Program, increasing Android zero-click payouts to $1.5 million while adjusting Chrome rewards amid an AI security surge.

Runtime Rebel Intel
4 min read · May 1, 2026
INFO
Threat Intel

Securing Agentic AI: CISA and International Partners Issue Guidance

CISA and international partners release guidance on securing agentic AI services, detailing risks like autonomous execution and supply chain vulnerabilities.

Runtime Rebel Intel
3 min read · May 1, 2026
HIGH
Threat Intel

AI-Powered Exploit Surge: Mitigating Automated Attack Development

Anthropic's Claude Security counters the emerging threat of AI-accelerated exploit generation, enhancing defense against novel vulnerabilities and attack vectors.

Runtime Rebel Intel
4 min read · May 1, 2026
AI Integration Blind Spots: Navigating Executive Security Risks
INFO
Threat Intel

AI Integration Blind Spots: Navigating Executive Security Risks

Executives face critical blind spots in AI adoption, from comprehension gaps to deployment complexity, posing significant security and competitive risks to organizations.

Runtime Rebel Intel
5 min read · Apr 30, 2026
HIGH
Vulnerabilities

Firefox 150 Patch: 271 Zero-Days Found via Claude Mythos — Update Now

Firefox 150 addresses 271 vulnerabilities discovered by Anthropic’s Claude Mythos AI model, highlighting a shift in automated vulnerability discovery.

Runtime Rebel Intel
4 min read · Apr 29, 2026
Defending the Zero-Window Era: AI-Driven Exploitation and NDR
CRITICAL
Threat Intel

Defending the Zero-Window Era: AI-Driven Exploitation and NDR

Anthropic’s Claude Mythos and Project Glasswing have eliminated traditional patching windows. Learn why NDR is essential for defending against AI-driven exploits.

Runtime Rebel Intel
4 min read · Apr 28, 2026
MEDIUM
Threat Intel

Malicious AI Prompt Injection Attacks: Google Red Team Insights

Google reports a surge in AI prompt injection attacks, highlighting low-sophistication attempts and strategies for mitigating indirect prompt injection risks.

Runtime Rebel Intel
4 min read · Apr 27, 2026
Anthropic Claude Mythos: Scaling Vulnerability Discovery and Remediation
MEDIUM
Threat Intel

Anthropic Claude Mythos: Scaling Vulnerability Discovery and Remediation

Claude Mythos Preview accelerates vulnerability discovery, forcing security teams to rethink remediation workflows and automated patch validation.

Runtime Rebel Intel
4 min read · Apr 27, 2026
Rethinking Threat Intelligence: Transitioning to Autonomous SOC Operations
INFO
Threat Intel

Rethinking Threat Intelligence: Transitioning to Autonomous SOC Operations

Examine the shift from manual analysis to autonomous action by 2026. Learn how AI agents and high-fidelity data bridge the gap between intel and remediation.

Runtime Rebel Intel
3 min read · Apr 25, 2026