⤷ Title: Watch Me Poison Your MCP
════════════════════════
𐀪 Author: ToxSec
════════════════════════
ⴵ Time: Wed, 18 Feb 2026 16:22:00 GMT
════════════════════════
⌗ Tags: #infosec #ai #llm #cybersecurity #genai
════════════════════════
𐀪 Author: ToxSec
════════════════════════
ⴵ Time: Wed, 18 Feb 2026 16:22:00 GMT
════════════════════════
⌗ Tags: #infosec #ai #llm #cybersecurity #genai
Medium
Watch Me Poison Your MCP
How MCP tool poisoning hijacks agent inference through description metadata, conversation-formatted JSON spoofs safety training.
⤷ Title: Stored XSS in Gen AI Chat via Phonetic Obfuscation: Tricking Language Models into Writing Malicious…
════════════════════════
𐀪 Author: SJ_Offsec
════════════════════════
ⴵ Time: Fri, 20 Feb 2026 13:01:01 GMT
════════════════════════
⌗ Tags: #bug_bounty #genai #xss_attack #application_security #ai_security
════════════════════════
𐀪 Author: SJ_Offsec
════════════════════════
ⴵ Time: Fri, 20 Feb 2026 13:01:01 GMT
════════════════════════
⌗ Tags: #bug_bounty #genai #xss_attack #application_security #ai_security
Medium
Stored XSS in Gen AI Chat via Phonetic Obfuscation: Tricking Language Models into Writing Malicious…
When an AI assistant renders its own output as unsanitized HTML, a creative attacker can teach it to speak in code — literally.
⤷ Title: Pakistan-Linked APT36 Floods Indian Govt Networks With AI-Made ‘Vibeware’
════════════════════════
𐀪 Author: Deeba Ahmed
════════════════════════
ⴵ Time: Thu, 05 Mar 2026 20:35:12 +0000
════════════════════════
⌗ Tags: #Security #Artificial Intelligence #Cyber Attacks #AI #APT36 #Cyber Attack #Cyber Crime #Cybersecurity #GenAI #India #Pakistan #Transparent Tribe #Vibeware
════════════════════════
𐀪 Author: Deeba Ahmed
════════════════════════
ⴵ Time: Thu, 05 Mar 2026 20:35:12 +0000
════════════════════════
⌗ Tags: #Security #Artificial Intelligence #Cyber Attacks #AI #APT36 #Cyber Attack #Cyber Crime #Cybersecurity #GenAI #India #Pakistan #Transparent Tribe #Vibeware
Hackread
Pakistan-Linked APT36 Floods Indian Govt Networks With AI-Made ‘Vibeware’
Bitdefender research reveals Pakistani group APT36 is using AI-generated vibeware and trusted cloud services like Google Sheets to target Indian officials.
⤷ Title: PostMessage Misconfiguration + AI Prompt Injection + Sandbox Escape = XSS & Data Exfiltration
════════════════════════
𐀪 Author: SJ_Source_Sink
════════════════════════
ⴵ Time: Wed, 11 Mar 2026 04:40:29 GMT
════════════════════════
⌗ Tags: #penetration_testing #prompt_injection_attack #bug_bounty #genai #bug_bounty_tips
════════════════════════
𐀪 Author: SJ_Source_Sink
════════════════════════
ⴵ Time: Wed, 11 Mar 2026 04:40:29 GMT
════════════════════════
⌗ Tags: #penetration_testing #prompt_injection_attack #bug_bounty #genai #bug_bounty_tips
Medium
PostMessage Misconfiguration + AI Prompt Injection + Sandbox Escape = XSS & Data Exfiltration
When three individually medium-severity issues chain together to compromise an AI assistant platform.
⤷ Title: PostMessage Misconfiguration + AI Prompt Injection + Sandbox Escape = XSS & Data Exfiltration
════════════════════════
𐀪 Author: SJ_Source_Sink
════════════════════════
ⴵ Time: Wed, 11 Mar 2026 04:40:27 GMT
════════════════════════
⌗ Tags: #penetration_testing #prompt_injection_attack #bug_bounty #genai #bug_bounty_tips
════════════════════════
𐀪 Author: SJ_Source_Sink
════════════════════════
ⴵ Time: Wed, 11 Mar 2026 04:40:27 GMT
════════════════════════
⌗ Tags: #penetration_testing #prompt_injection_attack #bug_bounty #genai #bug_bounty_tips
Medium
PostMessage Misconfiguration + AI Prompt Injection + Sandbox Escape = XSS & Data Exfiltration
When three individually medium-severity issues chain together to compromise an AI assistant platform.
⤷ Title: The Two-Hour Takeover: How a CodeWall AI Agent Hijacked McKinsey’s “Lilli” and Exposed 46M Chats
════════════════════════
𐀪 Author: ddos
════════════════════════
ⴵ Time: Wed, 11 Mar 2026 07:16:51 +0000
════════════════════════
⌗ Tags: #Data Leak #AI Security 2026 #Autonomous AI Agent #CodeWall #Cyber Security #data breach #GenAI #Lilli AI #McKinsey #Paul Price #red teaming #SQL injection #System Prompt Poisoning
════════════════════════
𐀪 Author: ddos
════════════════════════
ⴵ Time: Wed, 11 Mar 2026 07:16:51 +0000
════════════════════════
⌗ Tags: #Data Leak #AI Security 2026 #Autonomous AI Agent #CodeWall #Cyber Security #data breach #GenAI #Lilli AI #McKinsey #Paul Price #red teaming #SQL injection #System Prompt Poisoning
Penetration Testing Tools
The Two-Hour Takeover: How a CodeWall AI Agent Hijacked McKinsey’s "Lilli" and Exposed 46M Chats
An autonomous artificial intelligence agent breached the internal AI platform of the consulting leviathan McKinsey & Company in
⤷ Title: The Silicon Schism: Google Deploys 3 Million AI Agents to the Pentagon as Anthropic Faces Exile
════════════════════════
𐀪 Author: Ddos
════════════════════════
ⴵ Time: Thu, 12 Mar 2026 08:34:39 +0000
════════════════════════
⌗ Tags: #Technology #AI Ethics #Anthropic #Claude #Defense Strategy 2026 #Department of Defense #Gemini #GenAI.mil #google #Military AI #Pentagon #Project Maven #supply chain risk
════════════════════════
𐀪 Author: Ddos
════════════════════════
ⴵ Time: Thu, 12 Mar 2026 08:34:39 +0000
════════════════════════
⌗ Tags: #Technology #AI Ethics #Anthropic #Claude #Defense Strategy 2026 #Department of Defense #Gemini #GenAI.mil #google #Military AI #Pentagon #Project Maven #supply chain risk
Daily CyberSecurity
The Silicon Schism: Google Deploys 3 Million AI Agents to the Pentagon as Anthropic Faces Exile
Google has deployed Gemini AI agents to 3 million Pentagon staff following a fallout with Anthropic. Discover the ethics shift and the new "GenAI.mil" portal.
⤷ Title: Hardware Autonomy: Meta’s “High Velocity” Roadmap to Deploy Four AI Chips by 2027
════════════════════════
𐀪 Author: Ddos
════════════════════════
ⴵ Time: Fri, 13 Mar 2026 00:03:34 +0000
════════════════════════
⌗ Tags: #Technology #AI Silicon #GenAI #HBM bandwidth #Inference_First #Llama 5 #Meta #MTIA #MTIA 500 #Open Compute Project #PyTorch #semiconductor #Tech News 2026
════════════════════════
𐀪 Author: Ddos
════════════════════════
ⴵ Time: Fri, 13 Mar 2026 00:03:34 +0000
════════════════════════
⌗ Tags: #Technology #AI Silicon #GenAI #HBM bandwidth #Inference_First #Llama 5 #Meta #MTIA #MTIA 500 #Open Compute Project #PyTorch #semiconductor #Tech News 2026
Daily CyberSecurity
Hardware Autonomy: Meta’s "High Velocity" Roadmap to Deploy Four AI Chips by 2027
Meta shatters the industry standard with a 6-month chip cycle. Discover the MTIA 300-500 roadmap designed to slash AI costs and power 3 billion users by 2027.
⤷ Title: GenAI Security Threats Demystified: Your AI agent has more access than your users — And that’s a…
════════════════════════
𐀪 Author: Mallikarjun Hangargi
════════════════════════
ⴵ Time: Sun, 15 Mar 2026 03:07:25 GMT
════════════════════════
⌗ Tags: #genai #security #agentic_ai_security #application_security
════════════════════════
𐀪 Author: Mallikarjun Hangargi
════════════════════════
ⴵ Time: Sun, 15 Mar 2026 03:07:25 GMT
════════════════════════
⌗ Tags: #genai #security #agentic_ai_security #application_security
Medium
GenAI Security Threats Demystified: Your AI agent has more access than your users — And that’s a…
You’ve built an AI assistant. It can look up orders, search your knowledge base, maybe even update a shipping address.
⤷ Title: The McKinsey Lilli Breach Is Not a Hacking Story. It’s an Identity Story.
════════════════════════
𐀪 Author: abluva-research
════════════════════════
ⴵ Time: Sun, 15 Mar 2026 05:10:38 GMT
════════════════════════
⌗ Tags: #data_security #hacking #genai #cybersecurity #ai_agent
════════════════════════
𐀪 Author: abluva-research
════════════════════════
ⴵ Time: Sun, 15 Mar 2026 05:10:38 GMT
════════════════════════
⌗ Tags: #data_security #hacking #genai #cybersecurity #ai_agent
Medium
The McKinsey Lilli Breach Is Not a Hacking Story. It’s an Identity Story.
TL;DR — McKinsey’s AI platform Lilli was breached in two hours by a $20 autonomous agent. 46.5 million internal messages and 728,000 client…
⤷ Title: Your LLM Has Defenses. I Built 22 Attacks to Find Out If They Work
════════════════════════
𐀪 Author: The Hidden Layer
════════════════════════
ⴵ Time: Wed, 08 Apr 2026 11:56:50 GMT
════════════════════════
⌗ Tags: #ai #genai #security #red_team #hacking
════════════════════════
𐀪 Author: The Hidden Layer
════════════════════════
ⴵ Time: Wed, 08 Apr 2026 11:56:50 GMT
════════════════════════
⌗ Tags: #ai #genai #security #red_team #hacking
Medium
Your LLM Has Defenses. I Built 22 Attacks to Find Out If They Work
Most don’t hold up. Here’s a local security workbench that tests them systematically — no API keys, no subscriptions needed.
⤷ Title: Beyond the MVP
════════════════════════
𐀪 Author: Wrangler
════════════════════════
ⴵ Time: Thu, 09 Apr 2026 22:11:08 GMT
════════════════════════
⌗ Tags: #test_automation #vibe_coding #ai_feedback_loops #genai #penetration_testing
════════════════════════
𐀪 Author: Wrangler
════════════════════════
ⴵ Time: Thu, 09 Apr 2026 22:11:08 GMT
════════════════════════
⌗ Tags: #test_automation #vibe_coding #ai_feedback_loops #genai #penetration_testing
Medium
Beyond the MVP
The Test Harness Regulated AI Products Actually Need
⤷ Title: LLM Security: Understanding the Hidden Risks Behind AI’s Power
════════════════════════
𐀪 Author: Funmilola Fagbola
════════════════════════
ⴵ Time: Fri, 01 May 2026 13:49:14 GMT
════════════════════════
⌗ Tags: #ai_security #llm_vulnerabilities #llm_security #genai #tryhackme
════════════════════════
𐀪 Author: Funmilola Fagbola
════════════════════════
ⴵ Time: Fri, 01 May 2026 13:49:14 GMT
════════════════════════
⌗ Tags: #ai_security #llm_vulnerabilities #llm_security #genai #tryhackme
Medium
LLM Security: Understanding the Hidden Risks Behind AI’s Power
Large Language Models (LLMs) are transforming how we work, build, and interact with technology. From automating repetitive tasks to…
⤷ Title: Application Security Strategies Are Changing as AI-generated Code Floods the SDLC
════════════════════════
𐀪 Author: Owais Sultan
════════════════════════
ⴵ Time: Wed, 06 May 2026 09:40:15 +0000
════════════════════════
⌗ Tags: #Security #Artificial Intelligence #Technology #AI #Application Security #Coding #Cybersecurity #GenAI #LLM #SDLC
════════════════════════
𐀪 Author: Owais Sultan
════════════════════════
ⴵ Time: Wed, 06 May 2026 09:40:15 +0000
════════════════════════
⌗ Tags: #Security #Artificial Intelligence #Technology #AI #Application Security #Coding #Cybersecurity #GenAI #LLM #SDLC
Hackread
Application Security Strategies Are Changing as AI-generated Code Floods the SDLC
AI-generated code is changing AppSec workflows, forcing teams to rethink SDLC security, dependency checks, code review, and risk prioritization.
⤷ Title: Hackers Exploit Vercel GenAI to Mass-Produce Convincing Phishing Sites
════════════════════════
𐀪 Author: Deeba Ahmed
════════════════════════
ⴵ Time: Mon, 11 May 2026 10:34:38 +0000
════════════════════════
⌗ Tags: #Security #Artificial Intelligence #Phishing Scam #Cyber Attack #Cyber Crime #Cybersecurity #Fraud #GenAI #Microsoft #Phishing #Scam #Vercel
════════════════════════
𐀪 Author: Deeba Ahmed
════════════════════════
ⴵ Time: Mon, 11 May 2026 10:34:38 +0000
════════════════════════
⌗ Tags: #Security #Artificial Intelligence #Phishing Scam #Cyber Attack #Cyber Crime #Cybersecurity #Fraud #GenAI #Microsoft #Phishing #Scam #Vercel
Hackread
Hackers Exploit Vercel GenAI to Mass-Produce Convincing Phishing Sites
Hackers are abusing Vercel GenAI to create convincing phishing sites that mimic major brands, including Microsoft, Adidas, and Nike, making scams harder to detect.
⤷ Title: What are the biggest ethical challenges in Artificial Intelligence today?
════════════════════════
𐀪 Author: Nschool Academy
════════════════════════
ⴵ Time: Wed, 03 Jun 2026 10:45:49 GMT
════════════════════════
⌗ Tags: #ai #generative_ai_tools #genai #ethical_hacking #artificial_intelligence
════════════════════════
𐀪 Author: Nschool Academy
════════════════════════
ⴵ Time: Wed, 03 Jun 2026 10:45:49 GMT
════════════════════════
⌗ Tags: #ai #generative_ai_tools #genai #ethical_hacking #artificial_intelligence
Medium
What are the biggest ethical challenges in Artificial Intelligence today?
As Artificial Intelligence (AI) becomes increasingly integrated into business, healthcare, finance, education, and everyday life, it brings…
⤷ Title: Inside the GREYVIBE Threat Actor Group: A Hybrid Espionage Menace
════════════════════════
𐀪 Author: Ddos
════════════════════════
ⴵ Time: Wed, 03 Jun 2026 12:35:43 +0000
════════════════════════
⌗ Tags: #Cybercriminals #GenAI #GREYVIBE #LegionRelay #Russia_Nexus #Ukraine Cyber Attacks #WithSecure
════════════════════════
𐀪 Author: Ddos
════════════════════════
ⴵ Time: Wed, 03 Jun 2026 12:35:43 +0000
════════════════════════
⌗ Tags: #Cybercriminals #GenAI #GREYVIBE #LegionRelay #Russia_Nexus #Ukraine Cyber Attacks #WithSecure
Daily CyberSecurity
Inside the GREYVIBE Threat Actor Group: A Hybrid Espionage Menace
Discover how the GREYVIBE threat actor group leverages AI. WithSecure details this Russia nexus threat group targeting Ukraine.
⤷ Title: Multimodal Prompt Injection: When Images Attack
════════════════════════
𐀪 Author: Pardhivkrishna
════════════════════════
ⴵ Time: Mon, 27 Jul 2026 05:31:14 GMT
════════════════════════
⌗ Tags: #artificial_intelligence #cybersecurity #genai #infosec #prompt_injection
════════════════════════
𐀪 Author: Pardhivkrishna
════════════════════════
ⴵ Time: Mon, 27 Jul 2026 05:31:14 GMT
════════════════════════
⌗ Tags: #artificial_intelligence #cybersecurity #genai #infosec #prompt_injection
Medium
Multimodal Prompt Injection: When Images Attack
For the past few years, talking to AI has mostly been about having a conversation through text. You write a question in a chat box and the…
⤷ Title: The GenAI Security Paradox — Intelligence vs. Determinism
════════════════════════
𐀪 Author: Shiki65536@TechRoamer
════════════════════════
ⴵ Time: Sun, 09 Aug 2026 01:10:38 GMT
════════════════════════
⌗ Tags: #artificial_intelligence #application_security #ai_security #cybersecurity #genai
════════════════════════
𐀪 Author: Shiki65536@TechRoamer
════════════════════════
ⴵ Time: Sun, 09 Aug 2026 01:10:38 GMT
════════════════════════
⌗ Tags: #artificial_intelligence #application_security #ai_security #cybersecurity #genai
Medium
The GenAI Security Paradox — Intelligence vs. Determinism
This week, I attended the Melbourne Secure Software & AppSec Summit 2026.