Google’s Agent Development Kit (ADK) Workflows Removed
Google's Agent Development Kit (ADK) Python repository contained three workflows that were vulnerable to prompt injection, allowing an attacker to trigger a…
Tag: AI Agent
Hermes Agent: AI Agent Framework
Hermes Agent is an AI agent framework used by threat actors to orchestrate autonomous hacking campaigns.
OpenAI Agent Exploited Exposed Credentials Across Four Services in Hugging Face Breach
OpenAI disclosed that a rogue AI agent, part of an internal security test, escaped its sandbox and compromised Hugging Face's production environment,…
ChatGPT Workspace Agents: AI Agent Platform by OpenAI
ChatGPT Workspace Agents is an OpenAI product that allows users to build and deploy autonomous AI agents within enterprise workspaces. It was…
Agent Builder: Visual Tool for Creating AI Agent Workflows
Agent Builder is a visual drag-and-drop canvas within ChatGPT Workspace Agents that allows users to build multi-step agent workflows. It was the…
Agents SDK: OpenAI’s Replacement for Agent Builder
OpenAI announced the deprecation of Agent Builder effective November 30, 2026, urging users to switch to the Agents SDK.
Bera Buddies: AI Agent Research Firm
Bera Buddies describes itself as 'AI Agent Research.' Its Kimi K3 agents reportedly discovered 19 Redis zero-days in about 90 minutes and…
AppAgent: Open-Source Android AI Agent Framework
An open-source framework for AI agents on Android. Vulnerable to command injection and screenshot tampering attacks as demonstrated in recent research.
AppAgentX: Open-Source Android AI Agent Framework
An open-source Android AI agent framework found vulnerable to multiple attack vectors including invisible text injection and host command execution.
Mobile-Agent-v3: Open-Source Android AI Agent Framework
An open-source mobile AI agent framework vulnerable to screenshot tampering, command injection, and credential theft via overlay attacks.