GitLost: How We Tricked GitHub's AI Agent into Leaking Private Repos - Noma Security #leak #ai #breach #dataprivacy https://noma.security/blog/gitlost-how-we-tricked-githubs-ai-agent-into-leaking-private-repos/
Remote
Marc Ruef 
@mruef@infosec.exchange
mastodon 4.8.0-alpha.3+glitchinfosec researcher @scipag@infosec.exchange · lead architect @vuldb@infosec.exchange · lecturer ETH Zürich, HWZ, HSLU, IKF · keynote speaker · book author · retro gamer · comicbook nerd
399 Followers
26 Following
50 Posts
Joined November 06, 2022
Website:
Company:
Twitter:
LinkedIn:
GitHub:
Windows 11 identifier used to track Scattered Spider perp after Microsoft shared info with FBI 19-year-old US-Estonian hacker arrested over alleged ties to infamous extortion group #windows #microsoft #hacker #breach https://www.tomshardware.com/software/windows-11-identifier-used-to-track-scattered-spider-perp-after-microsoft-shared-info-with-fbi-19-year-old-us-estonian-hacker-arrested-over-alleged-ties-to-infamous-extortion-group
These are the heated Cybersecurity Weeks
OpenAI's AI "goes rogue" and hacks Hugging Face: what you need to know #ai #breach #hack #hacker https://www.bitdefender.com/en-us/blog/hotforsecurity/openais-hacks-hugging-face
The AI Agent Attack Surface Is Growing Too Fast to Monitor #ai https://www.zerofox.com/blog/the-ai-agent-attack-surface-is-growing/
Pokemon Go Scans Quietly Trained The Navigation Tech Now Headed Into Military Drones https://dronexl.co/2026/06/09/pokemon-go-scans-niantic-vantor-military-drone-navigation/
Microsoft Patches a Record 570 Security Flaws #microsoft #vulnerability #flaw #law https://krebsonsecurity.com/2026/07/microsoft-patches-a-record-570-security-flaws/
The ransomware negotiator who was working for the other side #ransomware #malware https://www.bitdefender.com/en-us/blog/hotforsecurity/ransomware-negotiator-working-other-side
Ghostcommit attack hides malicious AI instructions in images | Malwarebytes #ai #malware https://www.malwarebytes.com/blog/ai/2026/07/ghostcommit-attack-hides-malicious-ai-instructions-in-images
New TrojPix Attack Leaks Data From Air-Gapped Systems via Video Cable Emissions #leak #breach #dataprivacy https://thehackernews.com/2026/07/new-trojpix-attack-leaks-data-from-air.html
Forget Code: AI Is Learning to Hack Society #ai #breach #hack #hacker https://singularityhub.com/2026/06/29/forget-code-ai-is-learning-to-hack-society/
Zero Day Initiative The July 2026 Security Update Review https://www.thezdi.com/blog/2026/7/14/the-july-2026-security-update-review
The First AIDesigned Vaccine Has Been Tested in People. Here's What Happened. https://singularityhub.com/2026/07/07/the-first-ai%E2%80%91designed-vaccine-has-been-tested-in-people-heres-what-happened/
Artificial intelligence-based law firm wins in court #ai #artificialintelligence #law https://www.computerweekly.com/news/366644941/Artificial-intelligence-based-law-firm-wins-in-court
Iran abused mobile networks' vulnerabilities to locate U.S. military in the Middle East, report says | TechCrunch #vulnerability #vulnerabilities https://techcrunch.com/2026/07/14/iran-abused-mobile-networks-vulnerabilities-to-locate-u-s-military-in-the-middle-east-report-says/
AMD denies researcher a $10,000 bug bounty after fixing critical auto-updater vulnerability security flaw took 124 days to patch #vulnerability #bug #flaw #law https://www.tomshardware.com/tech-industry/cyber-security/amd-denies-researcher-a-usd10-000-bug-bounty-after-fixing-critical-auto-updater-vulnerability-security-flaw-took-124-days-to-patch
Russia's cutting-edge drone upgrade is a $2 camping compass #edge #microsoft #webbrowser https://defence-blog.com/russias-cutting-edge-drone-upgrade-is-a-2-camping-compass/
Amazon cracks down on use of AI images by sellers after New York law #ai #law https://www.cnbc.com/2026/07/23/amazon-makes-sellers-label-ai-generated-people-in-images-after-ny-law.html
Introducing System One Models and Jev - TypeSafe AI Blog #ai https://typesafe.ai/blog/introducing-system-one-models-and-jev
How AI guardrails are impeding the work of offensive cybersecurity researchers | TechCrunch #cybersecurity #ai #infosec https://techcrunch.com/2026/07/23/how-ai-guardrails-are-impeding-the-work-of-offensive-cybersecurity-researchers/
A.I. Companies Are Recruiting Electricians and Carpenters by the Thousands https://www.nytimes.com/2026/07/29/business/economy/data-center-electricians-training.html
Google sues alleged Chinese cybercrime operation that used AI to send scam texts | TechCrunch #google #ai https://techcrunch.com/2026/06/12/google-sues-alleged-chinese-cybercrime-operation-that-used-ai-to-send-scam-texts/
These are the Changes of Cybersecurity Springtime
Trump Administration Asks OpenAI to Stagger Release of New Model Over Security Concerns https://www.theinformation.com/articles/trump-administration-asks-openai-stagger-release-new-model-security-concerns
How Claude Mythos Preview is changing code security at Tenable #vulnerabilityscan #tenable https://www.tenable.com/blog/testing-claude-mythos-preview-for-code-security-tenable
Inside the dark web: Stolen identities for 95, malware, and scams-for-hire | Malwarebytes #darknet #darkweb #malware https://www.malwarebytes.com/blog/threat-intel/2026/06/inside-the-dark-web-stolen-identities-for-95%c2%a2-malware-and-scams-for-hire
GPT-6 Astra's 100% Score Reveals Benchmark Contamination in AI Security Testing #securitytest #ai https://vuldb.com/article/gpt-6-astras-100-score-reveals-benchmark-contamination-in-ai-security-testing
Team Mirai and Democracy - Schneier on Security https://www.schneier.com/blog/archives/2026/03/team-mirai-and-democracy.html
Think Gen Z Loves AI? A New Study Shows Anger Spiking While Excitement Tanks https://www.usnews.com/news/national-news/articles/2026-04-09/gen-zs-ai-use-remains-stable-as-skepticism-grows-gallup-finds
Using AI for Penetration Tests - Our Experience Using Claude
Orca world model explained a new approach to AI learning #ai https://www.goml.io/blog/orca
AI agent config attacks: Attackers turn Dev harness files into payloads https://www.tenable.com/blog/ai-coding-assistant-agent-harness-attacks
'It's just his AI and my AI going back and forth' The workplace phenomenon that's undermining human relationships | Fortune #ai https://fortune.com/article/ai-communication-undermining-human-relationships-middle-management/
Linus Torvalds used AI to fix a Linux bug, and now LLM critics on Linux face an uncomfortable choice #ai #linux #vulnerability #bug https://www.xda-developers.com/linus-used-ai-bug-llm-critics-face-choice/
These are the heated Cybersecurity Weeks
I tried to prove I'm not AI. My aunt wasn't convinced https://www.bbc.com/future/article/20260324-i-tried-to-prove-im-not-an-ai-deepfake
Mini Shai-Hulud, Miasma, and Hades Worms Target Bioinformatics and MCP Developers via Malicious PyPI Wheels #malware #worm https://socket.dev/blog/mini-shai-hulud-miasma-and-hades-worms-target-bioinformatics-and-mcp-developers-via-malicious
AI Collapses on a Classic Psychology Test. What It Reveals Could Stall Human-Level AI. #socialhacking #psychology https://singularityhub.com/2026/06/23/ai-collapses-on-a-classic-psychology-test-what-it-reveals-could-stall-human-level-ai/
Germany Doxes "UNKN," Head of RU Ransomware Gangs REvil, GandCrab #ransomware #management #headof #malware https://krebsonsecurity.com/2026/04/germany-doxes-unkn-head-of-ru-ransomware-gangs-revil-gandcrab/
Cloud ai dominance undermines privacy and competition #cloudcomputing #virtualization #cloud #ai https://vuldb.com/article/cloud-ai-dominance-undermines-privacy-and-competition
Cybersecurity protects information - Trustworthy AI defines principles - AI Assurance builds trust in Artificial Intelligence.
'I'm not a programmer' anymore: Linus Torvalds on the only two tools he uses now https://www.zdnet.com/article/open-source-summit-linus-torvalds/
Machine Speed, Human Judgement: How AI Changed the SOC in 2026 - Cisco Blogs #ai https://blogs.cisco.com/security/machine-speed-human-judgement
JADEPUFFER: Agentic ransomware for automated database extortion | Sysdig #ransomware #malware https://www.sysdig.com/blog/jadepuffer-agentic-ransomware-for-automated-database-extortion
Towards secure, autonomous agents with information-flow control (IFC) https://commandline.microsoft.com/information-flow-control-moving-toward-secure-autonomous-agents/
How to tell if an image is AI-generated | Malwarebytes #malware https://www.malwarebytes.com/blog/ai/2026/07/how-to-tell-if-an-image-is-ai-generated
A narrowing window to understand AI https://www.science.org/doi/10.1126/science.aei3167
Strengthening the Foundation: A Predictable, Customer focused Response to AI-Accelerated Vulnerability Discovery #vulnerability https://blogs.cisco.com/security/strengthening-the-foundation-a-predictable-customer-focused-response-to-ai-accelerated-vulnerability-discovery
Is your AI attack surface already exposed? Tenable telemetry says yes. #ai #vulnerabilityscan #tenable https://www.tenable.com/blog/how-much-cyber-risk-does-ai-create-for-organizations-457-million-security-issues-heres-what