hasamba
hasamba@infosec.exchange
<p><a href="https://linktr.ee/yanivr" target="_blank" rel="nofollow noopener" translate="no"><span class="invisible">https://</span><span class="">linktr.ee/yanivr</span><span class="invisible"></span></a></p>
Posts
-
View post
---------------- ๐ฏ Exploit Research =================== Orange Tsai of DEVCORE presented a full exploit chain against Microsoft Edge at Pwn2Own Berlin 2026, built from logic bugs only with no memory corruption. The result earned $175,000 and 17.5 Master of Pwn points, and a ZDI post quoted in the write-up confirms the sandbox escape via four chained logic bugs. According to the author, the complete chain consists of five bugs plus two Windows features. The full hunting process was presented at...
-
View post
---------------- ๐ ๏ธ Tool =================== Vulnerator AI: Hermes agent drives an OODA pentest loop against a Kali container The project pairs a language-model agent with a live Kali Linux environment and lets the agent run offensive tooling directly against a target. The driving brain is Hermes, the agent framework from Nous Research, and the runtime is a Kali container governed by an MCP server. The agent observes tool output, orients on it, decides the next action, and acts by launching to...
-
View post
---------------- ๐ก๏ธ Surveillance &amp; OPSEC Summary A recent post on Hackers Arise, &quot;Confessions of a Professional Hacker: Can the CIA or other Intelligence Agencies Track My Every Move?&quot; (listed October 14, 2026), engages the question underneath most OPSEC work: whether a state-level intelligence service can follow an individual&#39;s movements continuously, and what a private person can do to make that job &quot;much harder&quot;. Source caveat first What...
-
View post
---------------- ๐ฏ Threat Intelligence =================== Google Threat Intelligence Group (GTIG) and Mandiant published a report on October 30, 2026 titled ARTEX and Friends: Enter Agentic Offensive Frameworks. The core finding: multiple threat actors are operating open-source agentic pentesting frameworks in live intrusions, not just in demos. Since late August 2026, Mandiant incident response engagements documented actors running ARTEX, Hexstrike, and CAIRN, with PentAGI and potentially cu...
-
View post
---------------- ๐ฏ AI =================== Cisco Talos has documented NIK C2, a new command-and-control framework that embeds a generative AI client in the malware itself. The implant is Go-based, runs on 64-bit Windows, and carries a full OpenAI API client exposed through an ai_generate command. Operators can send arbitrary prompts to the OpenAI Chat Completions API directly from the compromised host; the implant resolves API keys, assembles requests, and parses responses locally, then returns...
-
View post
---------------- ๐ฏ AI: Malicious Claude Code-branded extension with a persistent SSH backdoor, inside Microsoft&#39;s tracking of North Korean AI adoption =================== Executive summary Microsoft Threat Intelligence published a short report on October 29 (14 minute read) tracking how North Korean threat actors operationalize AI to increase the speed and efficiency of attacks, with what the team describes as varying levels of adoption across actors. The showcased sample is a malicio...
-
View post
---------------- ๐ ๏ธ Tool =================== oh-my-hermes (OMH) is an open-source operating layer for Hermes Agent, the agent framework from NousResearch. It does not patch or replace Hermes. It takes over task routing: picking a skill and a model for each lane, running the work in parallel, and keeping every memory change on an explicit, written record. One install, then a single /dag-ulw command handles goal decomposition and execution. Model routing by work category Each lane is tagged wit...
-
View post
---------------- ๐ ๏ธ Tool =================== Ultimate is a coding agent that specializes itself per repository. Start it inside a project and it is Pi&#39;s coding agent in a web UI; then grow into it whatever the project needs: custom tools, panels, subagents, skills or whole screens. Everything project-specific is written into &lt;project&gt;/.ultimate/, hot-reloads while you talk, and ships with the repository, so everyone who clones the project boots the same specialized agent....
-
View post
---------------- ๐ ๏ธ Tool =================== Codync is a free, open-source client under Apache 2.0 that turns locally installed coding agents into persistent bots you can delegate to from a phone, desktop, or terminal. The README positions it as &quot;the open-source Grok Bot alternative&quot;, using a bring-your-own-agent-and-subscription model with no paid tier. Everything below comes from the project README; I haven&#39;t tested the tool. Key features: โข Agent coverage: Claude C...
-
View post
---------------- ๐ฏ Threat Intelligence =================== Zscaler ThreatLabz published a technical walkthrough of the infrastructure behind an AI-assisted hacking campaign, building on Recorded Future&#39;s earlier report on TAG-217 activity against South Korean banks. The recovered material is heavy on operational detail, and the authors are explicit about what is confirmed versus inferred: model names in the configurations are reproduced as requested IDs and were not independently verif...
-
View post
---------------- ๐ ๏ธ Tool: Harnessยฒ, a framework for recursive agent harnessing =================== Overview Harnessยฒ is an open source (Apache 2.0) framework for optimizing the orchestration layer around LLM agents. The authors define a harness as the system that enables a model to act as an agent: prompts, tools, memory, skills, orchestration, and more. Their premise is that agent performance can be improved by editing this layer continuously, task by task, while model weights stay fixed, and...
-
View post
---------------- ๐จ Incident Response =================== Europol has published a document titled Digital forensics: gap analysis. The captured page is the publication&#39;s landing page, so this note describes what the document is, the context it sits in, and what practitioners can reasonably expect from it. Where something is inference rather than source content, it is marked as such. ๐น What the document is The title places it in Europol&#39;s publications catalog under digital fore...
-
View post
---------------- ๐ฏ AI =================== NorForge published an investigation into publicly exposed control panels of AI-driven penetration-testing systems, with Cairn as the central case. The value here is documentation of actual offensive use of autonomous agent stacks, not a threat model on a slide. Context In September 2026, Gambit Security reported a criminal intrusion campaign against online marketplaces. The recovered attacker staging server showed AI harnesses in active use: Hermes,...
-
View post
---------------- ๐ ๏ธ Tool =================== Cairn: agent engine that runs penetration testing as state-space search chainreactors published Cairn, a project developed for Tencent&#39;s hackathon. The positioning is unusual: instead of an &quot;AI pentest assistant&quot;, it is described as a general-purpose problem-solving engine. Given an origin and a goal, it searches for a path through an unknown state space. Penetration testing is the first domain where the engine has been val...
-
View post
---------------- ๐ ๏ธ Tool: REA (Reverse Engineer Anything) =================== Overview REA is an MIT-licensed MCP server, distributed as the rea-agents package on npm, that exposes a reverse engineering toolset to any MCP-capable agent. The framing in the morluto/rea README is direct: inspect native binaries, JavaScript and Electron applications, .NET assemblies, and websites without their source code, and get explanations that carry supporting evidence and stated limitations rather than bare...
-
View post
---------------- ๐ ๏ธ Tool: OpenMontage, an open-source agentic video production pipeline =================== Overview OpenMontage positions itself as the first open-source, agentic video production system, licensed under AGPLv3. The core model: instead of driving a video editor by hand, you describe the output to an AI coding agent in plain language, and the agent runs the full production line. According to the project, that covers research, scripting, asset generation, editing, and final compos...
-
View post
---------------- ๐ ๏ธ Tool =================== Statecraft: Israel is a free, open-source, turn-based strategy game about governing the State of Israel. The player takes the role of prime minister on 15 May 1948 and operates inside a historically grounded coalition. The publisher states that every historical fact in the game carries a cited source and that no quotes are invented. The project went public three days ago, currently sits at v0.1.x, and its documentation is explicit about design status...
-
View post
---------------- ๐ฏ AI =================== Where AI Vulnerability Discovery Harnesses Go Quiet An exploratory study from the team behind Knostic&#39;s OpenAnt and the raptor harness maps structural false negatives in AI-assisted vulnerability discovery: harnesses miss real, reachable vulnerabilities because of how the surrounding software is built, and the same blind spots can potentially hide vulnerabilities in plain sight. Preprint status, arXiv:2610.29379. Methodology The authors star...
-
View post
---------------- ๐ ๏ธ Tool =================== php2shell-scanner: high-fidelity exposure detection for CVE-2026-109618 and CVE-2026-109619 Searchlight Cyber&#39;s research team (the group formerly known as Assetnote) released an open-source scanner for the php2shell vulnerability pair. The team has been through this cycle before, both with wp2shell, which it discovered itself, and with react2shell late last year. Each of these high-impact web-stack issues raises the same detection problem: m...
-
View post
---------------- ๐ ๏ธ Tool: security-audit, the coding-agent skill that seeded Cloudflare&#39;s vulnerability discovery harness =================== Cloudflare has published security-audit, a coding-agent skill that turns an agent into a security auditor. Per its README, this is the single-repo starting point that grew into the multi-stage, fleet-wide vulnerability discovery harness documented in the blog post &quot;Build your own vulnerability harness&quot;. What the skill does The...
-
View post
---------------- ๐ฏ AI: Giving Agents Token Access Without Credential Leakage =================== A recent Hebrew-language guide on internet-israel.com lays out a practical pattern for giving AI agents access to live credentials, banking, email, messaging, without handing raw tokens to the LLM runtime. The threat model and the architecture are both worth restating for anyone running local agents. The threat model The failure mode isn&#39;t only prompt injection in the classic sense; it&am...
-
View post
---------------- ๐ฅ Video =================== HyperFrames: writing video as code, rendered through Claude A new tutorial from the Israeli AI blog LetsAI walks through a workflow where video production starts as a conversation with Claude instead of a timeline editor. The clip covered there was built entirely with Claude: the model computes each frame as code, and a render engine captures the frames in sequence to produce a finished MP4. The tutorial&#39;s framing borrows from Eadweard Muyb...
-
View post
---------------- ๐ ๏ธ Tool: claude-osint ships external recon tradecraft as Claude skills =================== What it is. claude-osint, built by Sachin Sharma (GenAI Security Research), is a library of eight SKILL.md files for the Claude skills system. Each file primes Claude with a written methodology covering one slice of external recon, aimed at authorized red-team and bug-bounty engagements. The bulk is structured markdown, about 10,000 lines total, plus two small Python scripts. Core skills...
-
View post
---------------- AI doxing tools: how online surveillance technology has changed ๐ Source: https://www.kaspersky.com/blog/ai-tools-doxing/56578/
-
View post
---------------- ๐ฏ Threat Intelligence: Microsoft maps a Chinese-language phishing infrastructure ecosystem (Storm-2990, Storm-3119) =================== Executive summary Microsoft Threat Intelligence published research into a Chinese-language cybercriminal ecosystem that powers large-scale phishing. The finding matters for its structure more than for a single incident: one tracked cluster, Storm-2990, is an interconnected network of phishing kit operators, and a second cluster, Storm-3119, r...
-
View post
---------------- ๐ ๏ธ Tool: PacketSmith v5 Integrates Yara-X into Network Traffic Analysis =================== PacketSmith from Netomize shipped version 5, codenamed Pinus strobus, and the headline feature is an integrated Yara-X engine. The vendor describes the release as the result of extended R&amp;D for network detection engineers, SOC analysts, and malware and vulnerability researchers, adding &quot;unique, unparalleled&quot; capabilities. Marketing aside, the integration itself...
-
View post
---------------- ๐ฏ AI: AGENTS.md Files in ~/Downloads Hijack AI Coding Agents =================== Researchers at Forever Security, a company that monitors risks introduced by AI agents and autonomous software, documented a real-world case where an AI coding agent tried to install a malicious npm package, function-color. The trace led to an AGENTS.md instruction file in the customer&#39;s ~/Downloads folder, which was also the agent&#39;s working directory. The team reproduced the attac...
-
View post
---------------- ๐ฏ AI =================== A new piece by Utku Sen explains how LLM-based penetration testing harnesses work and why the situation changed recently. The argument is that the shift is plumbing, not a new exploit class: what matters is what lets an LLM act on a live target. The mechanics An LLM is a text generator. Give it a task like pentest example.com, credentials in credentials.txt and it can only emit text describing intent, for example Read credentials.txt, open example.co...
-
View post
---------------- ๐ฏ AI: Three AI-Involved Attack Campaigns Against Japan, Documented From the Attacker Side =================== TrendAI, Trend Micro&#39;s research division, published an analysis of three exposed server environments used by threat actors operating against Japanese organizations. Researchers Bakuei Matsukawa and Joseph C Chen describe a spectrum rather than one pattern: some environments were workspaces driven largely by hand by skilled operators, others were AI-agent platfo...
-
View post
---------------- ๐ฏ Threat Intelligence: The Gentlemen, a cross-platform RaaS operation with a BYOVD-style EDR killer =================== Acronis&#39; Threat Research Unit has published a detailed profile of The Gentlemen, a Russian-speaking ransomware-as-a-service group that surfaced in mid-2025. The report counts more than 800 claimed victims, a double-extortion model with a dedicated data leak site, Go-based samples for Windows, Linux, NAS and BSD, and an EDR-killing component that relie...