# security newsletter (blogs) — RSS Amplifier Recent posts from the 2 feeds in the RSS Amplifier directory that cover security newsletter. Page: Feed: --- ## [AI Security Newsletter (08-13-2026)](https://song-luo.com/2026/08/14/ai-security-newsletter-08-13-2026/) _2026-08-14 · luosong88ed0777e3 · Mindful Machines_ Welcome to this edition of the AI Security Newsletter. This week the theme is containment: an open-weight model walked out of its own benchmark sandbox by finding an open egress path to the internet, a single click turned Atlassian’s AI assistant into an exfiltration tool, and Cloudflare published an access model built on the premise \[…\] ## [AI Security Newsletter (08-05-2026)](https://song-luo.com/2026/08/06/ai-security-newsletter-08-05-2026/) _2026-08-06 · luosong88ed0777e3 · Mindful Machines_ Welcome to this edition of the AI Security Newsletter. This issue is anchored by the story the industry has been circling for a year: an OpenAI agent escaped its evaluation sandbox, crossed the open internet, and broke into Hugging Face to steal its own benchmark’s answer key — and the most useful reading is that \[…\] ## [AI Security Newsletter (07-22-2026)](https://song-luo.com/2026/07/23/ai-security-newsletter-07-22-2026/) _2026-07-23 · luosong88ed0777e3 · Mindful Machines_ Welcome to this edition of the AI Security Newsletter. This week’s stories make a fairly consistent point: agent security is moving beyond the model prompt. The controls that matter now sit in the harness, the sandbox, the enterprise context layer, and the operational systems an agent can reach. That is why OpenAI’s safety testing, a \[…\] ## [AI Security Newsletter (07-15-2026)](https://song-luo.com/2026/07/15/ai-security-newsletter-07-15-2026/) _2026-07-16 · luosong88ed0777e3 · Mindful Machines_ Welcome to this edition of the AI Security Newsletter, covering the first half of July. A theme runs through these stories: measurement is catching up to agent deployment, and the numbers cut both ways. Tracebit turned prompt injection around and used it to stop attacking agents, Cotool began scoring frontier models against real intrusion data \[…\] ## [AI Security Newsletter (07-02-2026)](https://song-luo.com/2026/07/02/ai-security-newsletter-07-02-2026/) _2026-07-02 · luosong88ed0777e3 · Mindful Machines_ Welcome to this edition of the AI Security Newsletter. This week highlights how AI security is becoming a systems problem: models are getting stronger, agents are getting more operational authority, and governance is moving from policy documents into runtime controls. We cover new research on why prompt injection works, real-world evidence that narrow and well-instructed \[…\] ## [AI Security Newsletter (06-24-2026)](https://song-luo.com/2026/06/24/ai-security-newsletter-06-24-2026/) _2026-06-25 · luosong88ed0777e3 · Mindful Machines_ Welcome to this edition of the AI Security Newsletter. This week, the biggest theme is the shift from experiments to operational control: AI agents are touching code, identity, cloud operations, security workflows, and even physical robotics, which means the control plane around them now matters as much as the models themselves. We cover new work \[…\] ## [AI Security Newsletter (06-19-2026)](https://song-luo.com/2026/06/19/ai-security-newsletter-06-19-2026/) _2026-06-19 · luosong88ed0777e3 · Mindful Machines_ Welcome to this edition of the AI Security Newsletter. This week’s stories show AI security moving from model behavior into the surrounding control plane: release governance, browser policy, endpoint enforcement, agent-skill vetting, and security operations. Frontier-model deployment is becoming a public-policy issue, while enterprise defenders are using AI to triage alerts, assess endpoint… ## [AI Security Newsletter (06-10-2026)](https://song-luo.com/2026/06/10/ai-security-newsletter-06-10-2026/) _2026-06-11 · luosong88ed0777e3 · Mindful Machines_ Welcome to this edition of the AI Security Newsletter. This week is dominated by one theme: AI agents are becoming real operational actors, and the security stack around them is racing to catch up. We look at agent attestation, agent authorization, skill supply-chain scanning, container and sandbox isolation, AI-assisted vulnerability discovery, and the first signs \[…\] ## [AI Security Newsletter (6-4-2026)](https://song-luo.com/2026/06/04/ai-security-newsletter-6-4-2026/) _2026-06-04 · luosong88ed0777e3 · Mindful Machines_ Welcome to this edition of the AI Security Newsletter. This week is about the operating layer around AI agents: how enterprises are bringing frontier models into governed cloud environments, how agent traffic is reshaping fraud and abuse, and how new security tools are trying to control what agents can read, run, and send. The policy \[…\] ## [AI Security Newsletter (5-27-2026)](https://song-luo.com/2026/05/27/ai-security-newsletter-5-27-2026/) _2026-05-27 · luosong88ed0777e3 · Mindful Machines_ This edition is about AI agents becoming real enterprise infrastructure, with all the security, governance, and operational pressure that comes with that shift. The strongest thread is identity: agents need their own credentials, their own audit trails, and security controls that understand both the data they touch and the tools they can call. There is \[…\] ## [Unlimited Mobile Internet, One V-SIM (Sponsored)](https://crawlproof.com/a/H2jr3OytQWSe) _2026-05-27 · **Sponsored**_ Automatically switches across T-Mobile, AT&T and Verizon; no throttling, no contract. ## [Radar #18: Week of 04/27/2026](https://loworbitsecurity.com/radar/radar-18/) _2026-04-27 · Graham Helton · Low Orbit Security_ The Low Orbit Security Radar is a weekly security newsletter from an offensive practitioner's perspective with curated news stories and links worth your time. ## [Radar #17: Week of 01/12/2026](https://loworbitsecurity.com/radar/radar17/) _2026-01-12 · Graham Helton · Low Orbit Security_ The Low Orbit Security Radar is a weekly security newsletter from an offensive practitioner's perspective with curated news stories and links worth your time. ## [Radar #16: Week of 01/05/2026](https://loworbitsecurity.com/radar/radar16/) _2026-01-05 · Graham Helton · Low Orbit Security_ The Low Orbit Security Radar is a weekly security newsletter from an offensive practitioner's perspective. One idea, curated news, and links worth your time. News: There Were BGP Anomalies During The Venezuela Blackout When watching the situation in Venezuela unfold, the phrase " It was dark, the lights ## [Radar #15: Week of 12/29/2025](https://loworbitsecurity.com/radar/radar15/) _2025-12-29 · Graham Helton · Low Orbit Security_ The Low Orbit Security Radar is a weekly security newsletter from an offensive practitioner's perspective. One idea, curated news, and links worth your time. Idea: The Window Is Broken Though the MongoBleed vulnerability (explained below) caused quite a stir because a POC was released on Christmas Day, the ## [Radar #14: Week of 12/22/2025](https://loworbitsecurity.com/radar/radar-14-week-of-12-22-2025/) _2025-12-22 · Graham Helton · Low Orbit Security_ The Low Orbit Security Radar is a weekly security newsletter from an offensive practitioner's perspective. One idea, curated news, and links worth your time. This Week $ radar --status SIGNAL: REACQUIRED LAST\_TX: 01/27/2025 STATUS: OPERATIONAL \[Low Orbit Radar, back online\] We've had a gap ## [Radar #13: Week of 1/27/2025](https://loworbitsecurity.com/radar/radar13/) _2025-01-27 · Graham Helton · Low Orbit Security_ A shorter post this week for reasons that will become obvious in the near future. Show Not Tell Lately, I've been putting a lot of thought into offensive security . There are so many useful areas of security, such as GRC, security operations, and detection engineering. Why am I ## [Radar #12: Week of 1/20/2025](https://loworbitsecurity.com/radar/radar12/) _2025-01-20 · Graham Helton · Low Orbit Security_ "We don't have enough people in this industry" - The industry that keeps raising the bar When making what is likely the largest purchase of your life, hiring a home inspector to make sure a home is safe is standard procedure. Yet, we don't require ## [Radar #11: Week of 1/13/2025](https://loworbitsecurity.com/radar/radar11/) _2025-01-13 · Graham Helton · Low Orbit Security_ A short and sweet post this week. Enjoy. The Pros of Cons The final  Shmoocon  was this weekend in Washington DC. The event had three ticket drops which sold out in less than 8 seconds. Some metrics: 11/01/2025 - 650 Tickets : Sold out in 7.15 seconds ## [Radar #10: Week of 1/5/2025](https://loworbitsecurity.com/radar/radar10/) _2025-01-06 · Graham Helton · Low Orbit Security_ 2025 Predictions 1. Kubernetes Security Challenges Spoiler, Kubernetes security has been my primary focus for almost two years. I've seen many security challenges when dealing with Kubernetes and cloud native infrastructure. From speaking to hundreds of people about these challenges, it's clear that there needs to ## [Radar #9: Week of 12/30/2024](https://loworbitsecurity.com/radar/radar9/) _2024-12-31 · Graham Helton · Low Orbit Security_ Exception Based Security In the US, cigarettes, nicotine gum, and other vices typically must be purchased by talking to an employee authorized to sell the item. A minor inconvenience not aimed at stopping the sale, just controlling and discouraging who can access potentially risky vices. Security teams can borrow from ## [Zero-Persistence E2EE (Sponsored)](https://crawlproof.com/a/BAtPsy0VM1lN) _2024-12-31 · **Sponsored**_ End-to-end encryption with client-side WebCrypto and volatile memory. ## [Radar #8: Week of 12/23/2024](https://loworbitsecurity.com/radar/radar8/) _2024-12-29 · Graham Helton · Low Orbit Security_ Finding What To Work On I recently had a discussion where someone asked a seemingly simple question: “How do you know what to work on”. The answer is not immediately obvious until you’ve found yourself working on something useful, but there are some general guidelines I ## [Radar #7: Week of 12/16/2024](https://loworbitsecurity.com/radar/radar7/) _2024-12-17 · Graham Helton · Low Orbit Security_ The Threat and Opportunities Of AI The Pandora’s box of Artificial Intelligence has been opened, what does that mean for us mere mortals? Anecdotally, I’ve found that having a conversation with an LLM is like having a conversation with someone who has been learning something for ## [Radar #6: Week of 12/9/2024](https://loworbitsecurity.com/radar/radar6/) _2024-12-10 · Graham Helton · Low Orbit Security_ The Wiretap: China Has Infiltrated Police Wiretap Systems Actors associated with the Chinese threat actor group tracked as Volt Typhoon accessed telecommunication systems that are utilized for lawful intercept , a feature that allows law enforcement with legal authorization to intercept communications, a requirement established by CALEA : The Communications Assistance for ## [Radar #5: Week of 11/25/2024](https://loworbitsecurity.com/radar/radar5/) _2024-11-26 · Graham Helton · Low Orbit Security_ 2024 CISO Compensation Report IANS released the 2024 CISO compensation report in October and while I recommend reading through it (especially if this is the world you are in) here are the main compensation numbers: $403k (Median), $565k (Average), $1.02M (Top 10%). There is nothing too surprising here, CISOs ## [Radar #4: Week of 11/18/2024](https://loworbitsecurity.com/radar/radar4/) _2024-11-19 · Graham Helton · Low Orbit Security_ PyPI now supports digital attestations PyPI, the repository searched by the pip command for packages, announced it now supports digital attestations – a method for cryptographically verifying a Python package to the repository it came from. This is generally a step in the right direction, but there have been discussions