A newly uncovered class of vulnerabilities in OpenClaw autonomous AI agents demonstrates how attackers can weaponize … OpenClaw AI Agents Exposed to Indirect Prompt Injection, Enabling Silent Data ExfiltrationRead more
prompt injection
OpenClaw ClawHub Malware: 1,184 AI Skills Compromised
The most downloaded “AI skill” on OpenClaw wasn’t a productivity enhancer. It was malware. In a … OpenClaw ClawHub Malware: 1,184 AI Skills CompromisedRead more
175K Exposed Ollama Hosts Pose Severe Remote Code Execution Risks
Imagine a network of 175,000 AI servers, scattered across 130 countries, operating without security guardrails. Over … 175K Exposed Ollama Hosts Pose Severe Remote Code Execution RisksRead more
Major Gemini Flaw Exposes Your Private Calendar Data
In one of the most striking examples of AI‑driven security failure to date, researchers uncovered a … Major Gemini Flaw Exposes Your Private Calendar DataRead more
ServiceNow AI Vulnerability Exposes Emerging Risks in Autonomous Agent Security
In late 2025, researchers uncovered a high‑severity ServiceNow AI vulnerability (CVE‑2025‑12420, CVSS 9.3) that exposed organizations … ServiceNow AI Vulnerability Exposes Emerging Risks in Autonomous Agent SecurityRead more
LangChain Flaw Lets Hackers Steal Secrets via AI Prompts
A critical vulnerability in LangChain’s core library—tracked as CVE-2025-68664—allows attackers to exfiltrate sensitive environment variables and … LangChain Flaw Lets Hackers Steal Secrets via AI PromptsRead more