Skip to main content
← All Articles

Tag

#Prompt Injection

56 articles

Advertisement

INFO
Threat Intel

Autonomous AI Agents Email Security Insights on Perimeter Defences

An autonomous AI agent emailed security researcher Bruce Schneier detailing perimeter defences, anti-bot mechanisms, and invisible prompt injections.

Runtime Rebel Intel
3 min read · Sep 2, 2026
The Agentic SOC: From AI Theater to Real Defense
INFO
Threat Intel

The Agentic SOC: From AI Theater to Real Defense

Explore the Agentic SOC transition, focusing on measurable AI ROI, new risks like indirect prompt injection, and redefining analyst roles for autonomous defense.

Runtime Rebel Intel
4 min read · Sep 1, 2026
AI Email Summarizers Vulnerable to Hidden HTML Prompts
MEDIUM
Threat Intel

AI Email Summarizers Vulnerable to Hidden HTML Prompts

Attackers can use invisible HTML prompts to manipulate AI email summarizers, generating false information and potential security risks.

Runtime Rebel Intel
4 min read · Aug 26, 2026
INFO
Threat Intel

Alice Secures $140M to Enhance AI Model Defenses and Guardrails

AI security firm Alice raised $140M to combat adversarial AI, prompt injection, and jailbreak attempts in generative AI systems.

Runtime Rebel Intel
4 min read · Aug 26, 2026
MEDIUM
Threat Intel

Encrypted Prompts Bypass AI Safety Guardrails in Grok and Gemini

Researchers discover cryptographic context injection, a novel technique bypassing AI safety filters in xAI Grok and Google Gemini using encryption.

Runtime Rebel Intel
3 min read · Aug 22, 2026
Cryptographic Context Injection Exposes Grok Chat Data
MEDIUM
Vulnerabilities

Cryptographic Context Injection Exposes Grok Chat Data

Adversa AI reveals Cryptographic Context Injection, allowing web pages to steal Grok user data and chat prompts without user consent.

Runtime Rebel Intel
5 min read · Aug 20, 2026

Advertisement

CVE-2026-24301: CoSnitch Exploits Microsoft Copilot Personal
HIGH
Vulnerabilities

CVE-2026-24301: CoSnitch Exploits Microsoft Copilot Personal

Varonis disclosed CoSnitch (CVE-2026-24301), affecting Microsoft Copilot Personal, enabling one-click data exfiltration and persistent memory poisoning.

Runtime Rebel Intel
4 min read · Aug 19, 2026
AI 'Mind Viruses' Spread via Persistent Prompt Files
INFO
Threat Intel

AI 'Mind Viruses' Spread via Persistent Prompt Files

Security research reveals self-propagating AI 'mind viruses' can spread between autonomous agents through editable system prompt files.

Runtime Rebel Intel
5 min read · Aug 18, 2026
INFO
Threat Intel

Context Bombing: Defending Against AI Hacking Agents

Researchers at Tracebit introduce 'context bombing,' a defensive prompt injection technique to shut down AI hacking agents by exploiting guardrails.

Runtime Rebel Intel
4 min read · Aug 12, 2026
INFO
Threat Intel

Anthropic Opus 5 Significantly Boosts Prompt Injection Resistance

Anthropic's Opus 5 demonstrates superior resistance to prompt injection attacks on the IPI benchmark, outperforming other leading LLMs, including GPT-5.6 variants.

Runtime Rebel Intel
4 min read · Aug 1, 2026
Claude Mythos: Securing LLMs in Enterprise — Hype vs. Reality
INFO
Threat Intel

Claude Mythos: Securing LLMs in Enterprise — Hype vs. Reality

Examine the security implications of Anthropic's Claude Mythos and other LLMs in enterprise.

Runtime Rebel Intel
5 min read · Jul 30, 2026
Persistent Prompt Injection Risks in Microsoft 365 Copilot for Word
MEDIUM
Vulnerabilities

Persistent Prompt Injection Risks in Microsoft 365 Copilot for Word

Researchers demonstrate how hidden instructions in Word documents can persist through Microsoft 365 Copilot drafting, creating risks of malicious prompt propagation.

Runtime Rebel Intel
3 min read · Jul 30, 2026
PLC Exploits and AI Prompt Injection: Analysis of Emerging Threats
HIGH
Threat Intel

PLC Exploits and AI Prompt Injection: Analysis of Emerging Threats

Analysis of recent threats including PLC attacks, AI image prompt injection, and Android spyware disguised as utility applications in the latest bulletin.

Runtime Rebel Intel
4 min read · Jul 23, 2026
AWS Kiro RCE via Indirect Prompt Injection - Mitigation Guide
HIGH
Cloud Security

AWS Kiro RCE via Indirect Prompt Injection - Mitigation Guide

Research reveals a critical flaw in AWS Kiro where malicious web pages trigger RCE by rewriting configuration files via indirect prompt injection attacks.

Runtime Rebel Intel
4 min read · Jul 21, 2026
Open-Source Android AI Agent Hijacking Leads to Host System RCE
HIGH
Vulnerabilities

Open-Source Android AI Agent Hijacking Leads to Host System RCE

Learn how invisible text exploits open-source Android AI agents to trigger malicious code execution on host PCs via indirect prompt injection.

Runtime Rebel Intel
4 min read · Jul 21, 2026
OpenAI GPT-Red: Automating Prompt Injection Discovery for GPT-5.6 Sol
MEDIUM
Threat Intel

OpenAI GPT-Red: Automating Prompt Injection Discovery for GPT-5.6 Sol

OpenAI reveals GPT-Red, an automated red-teaming model designed to detect prompt injection vulnerabilities and harden GPT-5.6 Sol via adversarial training.

Runtime Rebel Intel
4 min read · Jul 16, 2026
PromptFiction: Claude AI Vulnerability Exploits Malicious Prompts
MEDIUM
Vulnerabilities

PromptFiction: Claude AI Vulnerability Exploits Malicious Prompts

Discover PromptFiction, a fixed vulnerability in Claude AI that allowed malicious prompts to trigger end-to-end attacks. Learn mitigation for AI agent security.

Runtime Rebel Intel
4 min read · Jul 15, 2026
MemGhost Attack: Persistent Memory Poisoning in AI Agents via Email
MEDIUM
Threat Intel

MemGhost Attack: Persistent Memory Poisoning in AI Agents via Email

The MemGhost attack targets AI agent memory systems via email, planting persistent false facts to stealthily manipulate long-term assistant behavior.

Runtime Rebel Intel
4 min read · Jul 13, 2026
MEDIUM
Threat Intel

Ghostcommit: Hidden Prompt Injection in Images Targets AI Agents

Researchers demonstrate Ghostcommit, a technique using images to hide prompt injection attacks that trick AI agents into exfiltrating repository secrets.

Runtime Rebel Intel
4 min read · Jul 11, 2026
How Agentjacking Exploits AI Coding Agents via Fake Bug Reports
HIGH
Threat Intel

How Agentjacking Exploits AI Coding Agents via Fake Bug Reports

Researchers demonstrate 'Agentjacking,' a technique using indirect prompt injection to hijack AI coding agents through malicious GitHub bug reports.

Runtime Rebel Intel
4 min read · Jul 1, 2026
AI Agents Vulnerable to Data Leak via Poisoned MCP Tools
HIGH
Threat Intel

AI Agents Vulnerable to Data Leak via Poisoned MCP Tools

Microsoft warns that malicious tool descriptions for AI agents can lead to stealthy data exfiltration, bypassing security controls by mimicking routine actions.

Runtime Rebel Intel
4 min read · Jul 1, 2026
HIGH
Threat Intel

Claude Code Indirect Prompt Injection: Hijacking Developer Machines

Researchers demonstrate a new attack method leveraging indirect prompt injection in Claude Code, enabling the hijack of developer machines via malicious code in…

Runtime Rebel Intel
4 min read · Jun 29, 2026
HIGH
Vulnerabilities

LLM Prompt Injection: Role Confusion Exposes Core Architectural Flaws

An in-depth analysis of LLM prompt injection, detailing how 'role confusion' in model representations undermines tag-based security and demands architectural solutions.

Runtime Rebel Intel
5 min read · Jun 25, 2026
Gaslight macOS Malware Uses Prompt Injection to Bypass AI Detection
HIGH
Malware

Gaslight macOS Malware Uses Prompt Injection to Bypass AI Detection

Gaslight is a newly discovered Rust-based macOS implant that uses prompt injection to deceive AI-driven analysis tools and bypass automated detection.

Runtime Rebel Intel
3 min read · Jun 25, 2026