Published file metadata, source observations, indicators, and research history in one bounded catalog.
Sources represented on this page. Publication and observation dates describe the content; successful batch dates describe local collection. A recent batch does not certify complete coverage or current provider availability.
2 sources: 0 stale, 0 needing attention, 0 paused, 0 unverified.
Stale means older than twice the recorded collection interval, with a minimum of one hour; without an interval, the threshold is 24 hours. Cached content remains available while a feed is stale, paused, or unverified.
The Kindle (ebook) edition of “Cybersecurity Attacks - Red Team Strategies” is currently free on Amazon. Grab your copy while it lasts and spread the word!
First reported Feb 04, 2021 16:00 UTCCatalog metadata updated Oct 13, 2026 14:55 UTCOpen evidence recordExcited to announce that I will be presenting at BSides Singapore this year. The topic is adversarial usage of virtual machines during lateral movement. And we will also cover threat hunting and detection ideas. I have been referring to this technique as the Shadowbunny over the years. :) The conferences is on September 24th-25th, it will be all virtual and free to attend. Check out the BSidesSG 2020 website and schedule for other talks and details.
First reported Aug 28, 2020 07:00 UTCCatalog metadata updated Oct 13, 2026 14:55 UTCOpen evidence recordThere are some neat TTPs that I don’t use frequently, and if the time arises, I need to dig up details again. So, I figured to write some of them down, starting with SSH Agent Hijacking. What is SSH Agent Hijacking? Short story, if you have keys added to an SSH Agent an adversary with root permissions can use them. If you forward the SSH Agent to another host, an adversary with root permission on that other host can exploit and leverage your keys as well.
First reported Oct 16, 2022 18:30 UTCCatalog metadata updated Oct 13, 2026 14:55 UTCOpen evidence recordIn this very short post I wanna talk mention The Silver Searcher, which I just learned about a few weeks ago. In the past I have written quite a bit about the importance of credential hunting for your organization and some cool built-in operating system indexing features that can be used as well. Of course grep and findstr are also in every red teamers toolbox. As part of a coding project I recently learned about “The Silver Searcher”, which is very fast and has some neat features built it. It’s focus is source code searching.
First reported Jul 28, 2021 18:44 UTCCatalog metadata updated Oct 13, 2026 14:55 UTCOpen evidence recordAt Black Hat Europe I did a fun presentation titled SpAIware and More: Advanced Prompt Injection Exploits. Without diving into the details of the entire talk, the key point I was making is that prompt injection can impact all aspects of the CIA security triad. However, there is one part that I want to highlight explicitly: A Command and Control system (C2) that uses prompt injection to remote control ChatGPT instances. Remote Controlling ChatGPT Instances! An adversary can compromise ChatGPT instances and have them join a central Command and Control system which provides updated instructions for all the remote controlled ChatGPT instances to follow over-time.
First reported Jan 07, 2025 04:30 UTCCatalog metadata updated Oct 13, 2026 14:55 UTCOpen evidence recordMany Windows applications and services are implemented using an automation infrastructure called Component Object Model (COM). COM has been around for decades and its useful for programming, sharing of code at binary level, usage from scripting languages, and well, red teaming. Wide Usage of Component Object Model Many products are implemented as COM objects, including Microsoft Office. Using PowerShell (or other languages) COM objects can be created to fully automate applications and services.
First reported Jul 05, 2021 20:00 UTCCatalog metadata updated Oct 13, 2026 14:55 UTCOpen evidence recordThis post is part of a series about Offensive BPF that I’m working on to learn how BPFs use will impact offensive security, malware and detection engineering. Click the “ebpf” tag to see all relevant posts. In the last post we talked about a basic bpftrace script to install a BPF program that runs commands upon connecting from a specific IP with a specific magic source port. This post will dive into this idea more by leveraging more a complex solution.
First reported Oct 07, 2021 03:00 UTCCatalog metadata updated Oct 13, 2026 14:55 UTCOpen evidence recordPass the Cookie made it into the latest 2600 magazine! Very excited about this! I was just walking around Capitol Hill and stopped by Ada’s Technical Books on 15th Avenue - a great coffee shop with lots of technical books. Right after walking in to grab a cup of tea, I saw the latest Hacker Quarterly. A few months back I submitted an article about “Pass the Cookie”, so I had to check, and the article got indeed published!
First reported Feb 15, 2020 23:48 UTCCatalog metadata updated Oct 13, 2026 14:55 UTCOpen evidence recordJust a list of useful notes when dealing with Macs. I’m pretty new to Macs and there might be other, better solutions to the challenges I had to sovle but these worked for me and I’m learning. :) Pivoting between accounts and keychain issues After pivoting on a target host and elevating to root it seems not possible to gain access to other keychains easily. It requires to know the password of the other account still. Just running
First reported Jan 06, 2019 04:34 UTCCatalog metadata updated Oct 13, 2026 14:55 UTCOpen evidence recordExcited to announce the book that I have been working on: Cybersecurity Attacks - Red Team Strategies Learn about the foundational tactics, techniques and procedures to elevate your red teaming skills and enhance the overall security posture of your organization by leveraging homefield advantage. Contents and Background Red Team Strategies covers aspects that are not as commonly discussed in literature, including chapters around building and managing a pen test team. However, there is still plenty of technical content included as well. It is not a typical pen test book that focuses on common tools, or walks the reader through the various stages of a pen test.
First reported Dec 03, 2019 01:09 UTCCatalog metadata updated Oct 13, 2026 14:55 UTCOpen evidence recordAs part of the Month of AI Bugs, serious vulnerabilities that allow remote code execution via indirect prompt injection were discovered. There was a period of a few weeks where multiple arbitrary code execution vulnerabilities existed in popular agents, like GitHub Copilot, Amazon Q, AWS Kiro,… During that time I was wondering if it would be possible to write an AI virus. Hence the idea of AgentHopper was born.
First reported Aug 30, 2025 03:20 UTCCatalog metadata updated Oct 13, 2026 14:55 UTCOpen evidence recordToday we cover Claude Code and a high severity vulnerability that Anthropic fixed in early June. The vulnerability allowed an attacker to hijack Claude Code via indirect prompt injection and leak sensitive information from the developer’s machine, e.g. API keys, to external servers by issuing DNS requests. Prompt Injection Hijacks Claude When reviewing or interacting with untrusted code or processing data from external systems, Claude Code can be hijacked to run bash commands that allow leaking of sensitive information without user approval.
First reported Aug 11, 2025 11:20 UTCCatalog metadata updated Oct 13, 2026 14:55 UTCOpen evidence recordAbout two weeks ago, DeepSeek released a new AI reasoning model, DeepSeek-R1-Lite. The news quickly gained attention and interest across the AI community due to the reasoning capabilities the Chinese lab announced. However, whenever there is a new AI I have ideas… Apps That Hack Themselves - The 10x Hacker There are some cool tests that can be done when pentesting LLM-powered web apps, I usually try some quick fun prompts like this one:
First reported Nov 29, 2024 22:00 UTCCatalog metadata updated Oct 13, 2026 14:55 UTCOpen evidence recordIf you are building ChatGPT plugins, LLM agents, tools or integrations this is a must read. This post explains how the first exploitable Cross Plugin Request Forgery was found in the wild and the fix which was applied. Indirect Prompt Injections Are Now A Reality With plugins and browsing support Indirect Prompt Injections are now a reality in the ChatGPT ecosystem. The real-world examples and demos provided by others and myself to raise awarness about this increasing problem have been mostly amusing and harmless, like making Bing Chat speak like a pirate, make ChatGPT add jokes at the end or having it do a Rickroll when reading YouTube transcripts.
First reported May 28, 2023 19:00 UTCCatalog metadata updated Oct 13, 2026 14:55 UTCOpen evidence recordLiteLLM is a popular AI gateway. It provides a unified interface to LLMs and simplifies governance. It also has access to the backend LLM provider keys. All of that makes it a high-value target. Not only for IP and data theft, but also for response modification and tool invocation. This post walks through a set of TTPs that red teams can integrate into authorized operations to demonstrate rerouting, interception, and modification of LLM traffic. We also cover things defenders can look out for.
First reported Aug 03, 2026 16:00 UTCCatalog metadata updated Oct 13, 2026 14:55 UTCOpen evidence recordA common attack vector that LLM apps face is data exfiltration, in particular data exfiltration via Image Markdown Injection is a common vulnerability. Microsoft fixed the vulnerability in Bing Chat, ChatGPT is still vulnerable as Open AI “won’t fixed” the issue, and Anthropic just mitigated this vulnerability in Claude. This post documents the Anthropic Claude data exfiltration vulnerability and the mitigation put in place. The Vulnerability - Image Markdown Injection As a quick recap, imagine a large language model (LLM) returns the following text:
First reported Aug 01, 2023 22:15 UTCCatalog metadata updated Oct 13, 2026 14:55 UTCOpen evidence recordThis post is part of a series about machine learning and artificial intelligence. Click on the blog tag “huskyai” to see related posts. Overview: How Husky AI was built, threat modeled and operationalized Attacks: The attacks I want to investigate, learn about, and try out In this post we are going to look at the “Repudiation Threat”, which is one of the threats often overlooked when performing threat modeling, and maybe something you would not even expect in a series about machine learning.
First reported Nov 10, 2020 23:00 UTCCatalog metadata updated Oct 13, 2026 14:55 UTCOpen evidence recordPreviously I talked about remotely debugging Chrome, and we also covered the latest Microsoft Edge browser along the way. These features allow an adversary to gain access to authentication tokens and cookies. See MITRE ATT&CK Technique T1539: Steal Web Session Cookie as well for this. What about Firefox? For a while I was wondering if (my favorite) browser Firefox has such debugging features as well, and how one could detect malware trying to exploit it.
First reported Jul 15, 2020 13:00 UTCCatalog metadata updated Oct 13, 2026 14:55 UTCOpen evidence recordSenator Bernie Sanders, Representative Ocasio-Cortez, and Senator Jeff Merkley introduced the Ban Flock Act on Friday, which would stop federal agencies from using automatic license plate readers.
First reported Oct 06, 2026 13:24 UTCCatalog metadata updated Oct 13, 2026 14:51 UTCOpen evidence recordCops are getting around a very important iPhone security feature; someone made an LLM torture chamber; and lawyers going wild with ChatGPT.
First reported Oct 08, 2026 16:11 UTCCatalog metadata updated Oct 13, 2026 14:51 UTCOpen evidence recordSen. Ron Wyden is seeking a privacy review report about the HIDTA license plate program.
First reported Oct 09, 2026 16:00 UTCCatalog metadata updated Oct 13, 2026 14:51 UTCOpen evidence record"I saw her go by, and I just started running her info on Flock."
First reported Oct 08, 2026 15:24 UTCCatalog metadata updated Oct 13, 2026 14:51 UTCOpen evidence recordAnd 404's Flock coverage cited in proposed legislation.
First reported Oct 06, 2026 14:08 UTCCatalog metadata updated Oct 13, 2026 14:51 UTCOpen evidence recordThat washer/dryer combo could be used by cops to identify a property.
First reported Oct 12, 2026 13:54 UTCCatalog metadata updated Oct 13, 2026 14:51 UTCOpen evidence recordThe public shared-host view reaches the newest 2,400 matching records. Narrow the filters or search an exact MD5, SHA-1, or SHA-256 value to reach a specific record.
A filename, label, or report mention alone does not establish maliciousness. Observation dates describe cited sources; collection dates describe this local metadata catalog. No malware samples are stored, fetched, or executed by these pages.