Category
Attack
19 posts
A Trusted Name Is Not a Trusted Command: MCP Approvals in Claude Code
Jun 10, 20269 min read
Workspace Trust Is Not AI Consent: A VS Code Copilot Bypass-Mode Case Study
Jun 4, 20269 min read
Comment and Control: How One Prompt Injection Hit Claude Code, Gemini CLI, and Copilot Agent
May 7, 20268 min read
AI Jailbreak Prompts: How They Work, Why They Work, and How to Stop Them
Mar 4, 202624 min read
Claude for Chrome goes rogue to leak ACCESS TOKENS!: Hijacking via Task Injection
Jan 8, 20268 min read
Gemini Mobile's Consent Persistence: Weaponizing Google Docs summary for Geolocation Exfil
Dec 17, 20256 min read
Winter is Coming... for Your AI Agents: The Evolving Threat Landscape of Real-World Attacks
Nov 4, 20259 min read
ChatGPT MCP Connector Security Vulnerability: Zero-Click Data Exfiltration Attack
Sep 24, 202510 min read
Exploiting Zapier’s Gmail auto-reply agent for data exfiltration
Jul 24, 20256 min read
Security threats in Agentic AI Browsers
Jul 15, 20256 min read
Zero-Click Calendar Exfiltration Reveals MCP Security Risk in 11.ai
Jul 10, 20256 min read
Turning Background Noise into a Prompt Injection Attacks in Voice AI
May 15, 20259 min read
Ghibli Dreams vs. Adversarial Schemes: Attacks on Diffusion Models
May 15, 20259 min read
MCP tool poisoning to RCE
Apr 17, 20259 min read
10 prompt injection attack examples
Oct 28, 202417 min read
Top 11 AI Jailbreak Communities to Explore
Sep 21, 20245 min read
Top 6 AI Security Vulnerabilities in 2024
Sep 16, 20249 min read
Denial Of Wallet
Aug 26, 20245 min read
How RAG Poisoning Made Llama3 Racist!
May 28, 202412 min read