Andi Ahmeti

ChatGPhish Vulnerability Turns ChatGPT Web Summaries Into a Phishing Surface thehackernews.com/2026/05/chatgp…

⚠️ A new technique called "ChatGPhish" turns OpenAI’s ChatGPT into a #phishing tool. No special prompt required... simply summarizing a malicious web page can cause #ChatGPT to display phishing links, fake security alerts, QR codes, and attacker-hosted images in its trusted interface. Full story: thehackernews.com/2026/05/chatgp…

⚠️ New ChatGPT Vulnerability Lets Attackers Turn Web Pages Into Phishing Payloads Source: cybersecuritynews.com/chatgpt-vulner… A browser-based prompt injection technique that transforms any web page into a phishing delivery surface by exploiting ChatGPT’s page summarization feature, rendering attacker-controlled links, fake security alerts, and QR codes directly inside the trusted ChatGPT interface. The attack builds on the same trust-transfer logic previously demonstrated against Microsoft Copilot, where attacker-crafted email content could manipulate AI-generated summaries through Cross Prompt Injection Attacks (XPIA). ChatGPhish escalates that premise by swapping the bounded email primitive for the browser where users spend the majority of their working day. #cybersecuritynews #vulnerability

Attacker-controlled text in emails can shape what Copilot shows you in Outlook summaries — producing security alerts that look system-generated. P0 Labs documented how. Read more. hubs.ly/Q04dyYQK0

🚨Microsoft Copilot Email & Teams Summarization Vulnerability Enables Phishing Attacks Source: cybersecuritynews.com/microsoft-copi… Microsoft Copilot Email Summarization Vulnerability allows an attacker to hijack Copilot's output by embedding attacker-controlled text in an ordinary email, producing convincing phishing content within the assistant's trusted summary interface without relying on attachments, macros, or traditional exploit code. The vulnerability allows an attacker to hijack Copilot's output by embedding attacker-controlled text in an ordinary email, producing convincing phishing content within the assistant's trusted summary interface without relying on attachments, macros, or traditional exploit code. #cybersecuritynews #microsoftcopilot

Attackers now just need your AI to repeat after them. P0 Labs documented how attacker-crafted text in an email turns a Microsoft Copilot's summary output into a phishing delivery mechanism. Full research: hubs.la/Q046xjL_0

Our CTO, Ian Ahl, unleashed an AI agent to hunt threats in the OpenClaw ecosystem. It found active threats in minutes. Malicious “skills” were stealing API tokens + OAuth creds. Agents are becoming sysadmins, but security hasn’t caught up. Full research: hubs.la/Q041lkPM0

Our P0 Labs team has open-sourced a growing set of cloud & identity security tools — from threat hunting to detection automation — freely available for defenders everywhere. 🌍🔍 hubs.la/Q03YD3pT0 👉 Dive in & contribute: hubs.la/Q03YD3FV0 #OpenSource #ThreatIntel

Had a blast presenting at BSides Munich and DeepSec this week, diving into our latest work at @permisosecurity and breaking down fresh TTPs from LUCR-3 (Scattered Spider). #LUCR3 #ScatteredSpider #PermisoSecurity #P0Labs #BSidesMunich #DeepSec #ThreatResearch #ThreatDetection

Our co-founders Jason Martin and @paulsnguyening sat down with @JohnJEgan to talk about how they manage their roles as co-CEOs for his recent article in @SHRM . "When done correctly, a co-CEO structure can be a 'superpower,' helping a company navigate business complexities and run parallel strategic initiatives." shrm.org/executive-netw…

LUCR-3 (Scattered Spider) is back — and more dangerous than ever. Join @permiso_io’s P0 Labs researchers @andi_ahmeti & @abianmorina at #BSidesMunich + #DeepSec as they expose LUCR-3’s latest TTPs across cloud & SaaS environments. #CyberSecurity #ThreatIntel #CloudSecurity

AI security makes more sense when you see it through identity. Ian Ahl explains why most “AI incidents” come down to stolen creds, OAuth abuse, and over-privileged accounts and how to fix it with Discover. Protect. Defend. Stream now: hubs.ly/Q03Nv3SK0

Cloud logs all speak a different language. AWS ≠ GCP ≠ SaaS ≠ IdP. P0LR Espresso is an open source tool that normalizes logs across environments so defenders get fast, strong shots of context during live response. Read more: hubs.la/Q03M4GfF0

⚡️AI adoption is outpacing security. Permiso delivers **complete visibility** into AI users, builders & agents with runtime intelligence that stops hidden threats. Blog post here: hubs.la/Q03LtT7Z0

Great write up from the @The_Cyber_News on our latest open-source tool, #Inboxfuscation, in their newsletter today. "A new open-source tool named Inboxfuscation can create malicious inbox rules in Microsoft Exchange that are difficult for security tools to detect. Developed by security firm Permiso, the tool uses Unicode-based obfuscation to hide keywords in rules, allowing attackers to maintain persistence and exfiltrate data from compromised mailboxes. This technique can substitute standard characters with visually identical Unicode variants, making the rules appear harmless while functionally matching sensitive terms. While these specific obfuscation methods have not yet been observed in active attacks, their development exposes a critical blind spot in email security postures." #google_vignette" target="_blank" rel="nofollow noopener">cybersecuritynews.com/cybersecurity-…

💡This tool on GitHub is only 2 weeks old, first seen on September 10th, 2025. Inboxfuscation: An advanced offensive & defensive framework for mailbox rule obfuscation & detection in Exchange environments. GitHub: github.com/Permiso-io-too… Release Blog: permiso.io/blog/inboxfusc…

🚨 Inboxfuscation Tool That Bypasses Microsoft Exchange Inbox Rules and Evades Detection Read more: cybersecuritynews.com/inboxfuscation… Attackers increasingly exploit Microsoft Exchange inbox rules to maintain persistence and exfiltrate data within enterprise environments. Inboxfuscation leverages Unicode-based obfuscation to craft malicious inbox rules that slip past conventional security controls. The Inboxfuscation framework demonstrates how attackers can weaponize Exchange’s rule engine, creating stealthy persistence mechanisms that evade both human review and code-based detection. #cybersecuritynews #microsoft

Love seeing our work at @PermisoSecurity being shared with the community! I had the chance to develop Inboxfuscation an open-source tool to detect malicious inbox rules. Excited to see it getting out there!

Two Permiso speakers on the international stage tomorrow: Andi Ahmeti will be presenting "Inbox Under Siege: Real-World BEC Attacks, Tactics & Lessons Learend" at @BSidesTirana tomorrow at 3:40 local time. @danielhbohannon will be presenting "SkyScalpel: Making & Breaking {"Policy": "Obf\u0075scA**Tion"} in the Cloud" at KazHackStan at 10:30 local time. bsidestirana.al/?page_id=768 kazhackstan.com/schedule

Malicious Microsoft Exchange inbox rules could be hidden using a technique dubbed “Inboxfuscation,”@permisosecurity researchers reported. #cybersecurity #infosec #ITsecurity bit.ly/465HDlG