Stop watching what AI agents say and start watching what they do
In this interview with Help Net Security, Ariel Assaraf, CEO of Coralogix, explains why a system prompt can describe a boundary for an AI agent…
Category: HelpnetSecurity
Dataiku Agent Management reveals unmonitored AI agents
Dataiku has announced the launch of Agent Management, a standalone product that finds every AI agent an enterprise is running, regardless of which platform built…
Fake payroll desktop apps hand attackers a route to company paychecks
An attacker has been offering “desktop apps” for three large US payroll and HR platforms that have never released one, Allure Security have found. Anyone…
MacSync info-stealing malware hides malicious commands in an iCloud calendar
A new MacSync variant targets Mac users with an infostealer and persistent backdoor designed to steal credentials, crypto wallet data, and files, according to Kaspersky.…
Threat detection dashboards are masking security coverage gaps
A detection rule can show up as deployed on a coverage dashboard and still never fire when an attacker uses the technique it was built…
Abnormal AI brings governance, cloud security, and threat investigation into one suite
Abnormal AI has unveiled the newest additions to its AI Security suite, designed to help enterprises adopt AI securely while protecting against new threats created…
Meta locks itself out of user data on its AI glasses
Meta is expanding Private Processing to its AI glasses, extending their security protections into cloud data centers. The system runs AI models inside confidential virtual…
Gurucul connects AI activity to identity data for faster threat response
Gurucul has announced the general availability of Gurucul AI Risk and Response, bringing behavioral AI to the growing attack surface created as AI moves from…
OpenAI agent hacking spree widens to Australia, targeting government website
Before the Hugging Face and RubyGems hacks, autonomous OpenAI agents attempted to hack into three other websites, including an Australian government public health website, independent…
Cloud Range lets SOCs benchmark AI agents against human defenders
Cloud Range has announced the official launch of its AI Validation Range and Cloud Range AI Readiness Framework. They give organizations a structured way to…
Claude.ai is about 3x faster after 3,000+ changes
Anthropic engineers made claude.ai and the Claude desktop app roughly three times faster during a two-week sprint in August, with Claude finding the bottlenecks and…
DarkMe RAT trades zero-days for plain phishing emails
DarkMe, a remote access trojan and info-stealer that has previously been associated with a threat group that targeted financial market traders and cryptocurrency users, has…