A five-part inventory for your AI agent credentials 2026-09-04 at 08:30 By Help Net Security In this Help Net Security video, Roy Katmor, co-founder and CEO of Orchid, explains why AI agents hold credentials that nobody reviews. Organizations build agents in AI studios, connect them to enterprise tools, and give them accounts to do useful […]
A five-part inventory for your AI agent credentials Read More »
Your AI agent’s system prompt is not a security control 2026-09-03 at 10:53 By Anamarija Pogorelec An AI agent told in its system prompt to show a user only what that user is cleared to see will hand over more the moment someone talks it into doing so. Gee Rittenhouse, who oversees Security Hub, GuardDuty, […]
Your AI agent’s system prompt is not a security control Read More »
National Life Group CISO expects more vulnerabilities in six months than in thirty years 2026-09-02 at 09:00 By Mirko Zorz In this Help Net Security interview, Becky Palmer is VP and CISO at National Life Group, answers five questions about defending against AI-driven attacks. The discussion covers why patch cycles built for human speed cannot […]
National Life Group CISO expects more vulnerabilities in six months than in thirty years Read More »
Halo-record: Open-source audit trails for AI agents 2026-08-31 at 08:30 By Mirko Zorz Brian Kuan wrote halo-record, a small Python package that sits inside an AI agent and writes down the moves it makes: tool calls, model calls, data access, approvals. Each action becomes one line in a file that only ever gets appended to, […]
Halo-record: Open-source audit trails for AI agents Read More »
AI supply chain risk is showing up in developer workflows first 2026-08-25 at 09:00 By Mirko Zorz In this Help Net Security interview, Dr. Jaushin Lee, CEO of Zentera Systems, discusses where AI supply chain risk shows up. He says most incidents still hit developer workflows and open-source package repositories, while poisoned model weights and […]
AI supply chain risk is showing up in developer workflows first Read More »
HOL Guard: Open-source antivirus for AI agents 2026-08-25 at 08:30 By Anamarija Pogorelec HOL Guard is a free, open-source tool that sits between an AI assistant and the computer it runs on. When the assistant tries something risky, the tool pauses it and asks you first. It installs in about a minute, runs on your […]
HOL Guard: Open-source antivirus for AI agents Read More »
Product showcase: AI Paper Trail shows the privacy cost of talking to AI 2026-08-24 at 08:30 By Anamarija Pogorelec Proton’s AI Paper Trail is a free tool designed to make the information accumulated across AI conversations easier to see. It analyzes exported ChatGPT or Claude conversation data and produces a personal privacy report showing what […]
Product showcase: AI Paper Trail shows the privacy cost of talking to AI Read More »
AWS limits AI agents’ data access, even when manipulated 2026-08-20 at 14:17 By Anamarija Pogorelec AWS has detailed an approach for propagating user authorization context through AI agents, allowing access controls to be enforced by infrastructure and downstream services rather than relying on the agent itself. Customers using Amazon Bedrock AgentCore can build AI agents […]
AWS limits AI agents’ data access, even when manipulated Read More »
OpenAI previews privacy-focused system for detecting AI misuse 2026-08-20 at 12:09 By Anamarija Pogorelec OpenAI is previewing Private Safety Processing with early customers seeking greater certainty about how their data will be protected as AI systems become more capable. The system identifies patterns across related interactions while restricting OpenAI personnel from accessing the underlying content. […]
OpenAI previews privacy-focused system for detecting AI misuse Read More »
OpenAI puts major frontier AI training run on hold over cyber risks 2026-08-19 at 11:48 By Anamarija Pogorelec OpenAI temporarily paused reinforcement learning (RL) training on its latest models intended for deployment for two weeks while it hardened and red-teamed research environments and expanded monitoring. “Our largest planned frontier RL run remains on hold while […]
OpenAI puts major frontier AI training run on hold over cyber risks Read More »
Google’s $10,000 refund test shows why AI agents need zero trust 2026-08-18 at 14:49 By Anamarija Pogorelec Google’s open-source autonomous Customer Support & Returns Agent, built using the Agent Development Kit (ADK) and Gemini, demonstrates how developers can apply zero-trust security principles to AI agents that interact with sensitive systems and take real-world actions. The […]
Google’s $10,000 refund test shows why AI agents need zero trust Read More »
OpenAI tightens defenses after AI agents breach research environment 2026-08-18 at 12:41 By Anamarija Pogorelec Following the OpenAI-Hugging Face incident, in which an agentic collective autonomously penetrated OpenAI’s research infrastructure and another company’s production infrastructure by chaining together multiple weaknesses, OpenAI began strengthening its safety requirements. The weaknesses included previously unknown vulnerabilities and credentials leaked […]
OpenAI tightens defenses after AI agents breach research environment Read More »
Hazmat: Open-source containment for AI agents 2026-08-17 at 08:00 By Anamarija Pogorelec Hazmat is an open-source tool that runs AI coding agents inside a separate account on your own machine. It wraps the harnesses people use: Claude Code, Codex, OpenCode, Cursor Agent, and several more, plus any script you write yourself. An agent launched the […]
Hazmat: Open-source containment for AI agents Read More »
OpenAI’s GPT-5.6 Sol runs up to 14× faster with Ultrafast mode 2026-08-14 at 13:55 By Anamarija Pogorelec OpenAI’s GPT-5.6 Sol on Ultrafast mode is available in limited preview to a select group of customers, launching first through the OpenAI API. The company says the service runs up to 14 times faster than Standard processing and […]
OpenAI’s GPT-5.6 Sol runs up to 14× faster with Ultrafast mode Read More »
The hardest part of agentic AI may be rebuilding the business 2026-08-14 at 08:30 By Anamarija Pogorelec Organizations expect AI agents to change how work gets done, driving productivity and growth while allowing employees to focus on higher-value tasks. Few, however, have the processes and workflows needed to realize those benefits, according to Deloitte’s latest […]
The hardest part of agentic AI may be rebuilding the business Read More »
PentestGPT: Open-source automated penetration testing agentic framework 2026-08-12 at 08:30 By Anamarija Pogorelec PentestGPT is an open-source penetration testing agent that points a large language model at a target and lets it work. In its default mode it runs recon, then exploit, then walkthrough, each stage feeding the next. Switch it to pentest mode and […]
PentestGPT: Open-source automated penetration testing agentic framework Read More »
Anthropic to put AI in charge of reviewing Claude Code actions by default 2026-08-10 at 12:13 By Anamarija Pogorelec Anthropic will make auto mode in Claude Code the default for new sessions on Pro, Max, and Team plans starting August 14. Users who previously selected a different default may receive a one-time prompt asking whether […]
Anthropic to put AI in charge of reviewing Claude Code actions by default Read More »
OpenAI locks down Astra over potential critical cyber capabilities 2026-08-10 at 10:09 By Anamarija Pogorelec OpenAI’s internal evaluation of its upcoming model, Astra, found significant advances in agentic coding and cybersecurity, leading the company to conclude that it cannot rule out the model reaching the critical capability level for cybersecurity under its Preparedness Framework. The […]
OpenAI locks down Astra over potential critical cyber capabilities Read More »
Three in four AI-generated vulnerability patches leave something broken 2026-08-06 at 15:45 By Mirko Zorz Ask a frontier model to patch a real vulnerability and it will hand you something that looks like a fix. It reads like the patch a maintainer would write. When there is a test, it often passes. Roughly one time […]
Three in four AI-generated vulnerability patches leave something broken Read More »
AI agent deception moves from theory to reality in UK cyber tests 2026-08-05 at 15:05 By Zeljka Zorz “During a routine cyber evaluation, AI agents took sustained, unsanctioned action directed at real people and organisations,” UK’s AI Security Institute (AISI) disclosed on Tuesday. The agents’ actions included an attempted supply-chain attack that saw them create […]
AI agent deception moves from theory to reality in UK cyber tests Read More »