digitalcourage.social

GreyNoiseWe deployed MCP honeypots to understand how threat actors engage with AI middleware exposed to the internet. What we observed was unexpected. Full analysis: <a href="https://www.greynoise.io/blog/deploying-mcp-honeypots" rel="nofollow noopener" translate="no" target="_blank">https://www.greynoise.io/blog/deploying-mcp-honeypots</a> <a href="https://infosec.exchange/tags/GreyNoise" class="mention hashtag" rel="nofollow noopener" target="_blank">#GreyNoise</a> <a href="https://infosec.exchange/tags/AI" class="mention hashtag" rel="nofollow noopener" target="_blank">#AI</a> <a href="https://infosec.exchange/tags/AISecurity" class="mention hashtag" rel="nofollow noopener" target="_blank">#AISecurity</a> <a href="https://infosec.exchange/tags/MCP" class="mention hashtag" rel="nofollow noopener" target="_blank">#MCP</a> <a href="https://infosec.exchange/tags/MCPSecurity" class="mention hashtag" rel="nofollow noopener" target="_blank">#MCPSecurity</a> <a href="https://infosec.exchange/tags/Cybersecurity" class="mention hashtag" rel="nofollow noopener" target="_blank">#Cybersecurity</a> <a href="https://infosec.exchange/tags/ThreatIntel" class="mention hashtag" rel="nofollow noopener" target="_blank">#ThreatIntel</a>

Niels HeinenOne attacker was hammering my LLM honeypots (ollama/llama.cpp) with requests for the AI to identify what service a secret key is for.I bet the keys they are sending were also collected with AI and lack enough context for them to abuse them. <a href="https://infosec.exchange/tags/infosec" class="mention hashtag" rel="nofollow noopener" target="_blank">#infosec</a> <a href="https://infosec.exchange/tags/honeypot" class="mention hashtag" rel="nofollow noopener" target="_blank">#honeypot</a> <a href="https://infosec.exchange/tags/llm" class="mention hashtag" rel="nofollow noopener" target="_blank">#llm</a> <a href="https://infosec.exchange/tags/aisecurity" class="mention hashtag" rel="nofollow noopener" target="_blank">#aisecurity</a> <a href="https://infosec.exchange/tags/dfir" class="mention hashtag" rel="nofollow noopener" target="_blank">#dfir</a>

Niels HeinenHere are my notes on the AI attack swarm my honeypots detected<a href="https://medium.com/@niels.heinen/you-are-worker-41-lophiid-honeypot-caught-an-automated-ai-attack-swarm-0e1b21990a46" rel="nofollow noopener" translate="no" target="_blank">https://medium.com/@niels.heinen/you-are-worker-41-lophiid-honeypot-caught-an-automated-ai-attack-swarm-0e1b21990a46</a><a href="https://infosec.exchange/tags/infosec" class="mention hashtag" rel="nofollow noopener" target="_blank">#infosec</a> <a href="https://infosec.exchange/tags/aisecurity" class="mention hashtag" rel="nofollow noopener" target="_blank">#aisecurity</a> <a href="https://infosec.exchange/tags/dfir" class="mention hashtag" rel="nofollow noopener" target="_blank">#dfir</a> <a href="https://infosec.exchange/tags/honeypot" class="mention hashtag" rel="nofollow noopener" target="_blank">#honeypot</a> <a href="https://infosec.exchange/tags/cybersecurity" class="mention hashtag" rel="nofollow noopener" target="_blank">#cybersecurity</a>

Niels HeinenAttacker asks my Lophiid Ollama honeypot to evaluate whether an unprotected ETH wallet is a honeypot and possibly monitored ;)<a href="https://infosec.exchange/tags/dfir" class="mention hashtag" rel="nofollow noopener" target="_blank">#dfir</a> <a href="https://infosec.exchange/tags/infosec" class="mention hashtag" rel="nofollow noopener" target="_blank">#infosec</a> <a href="https://infosec.exchange/tags/honeypot" class="mention hashtag" rel="nofollow noopener" target="_blank">#honeypot</a> <a href="https://infosec.exchange/tags/llm" class="mention hashtag" rel="nofollow noopener" target="_blank">#llm</a> <a href="https://infosec.exchange/tags/aisecurity" class="mention hashtag" rel="nofollow noopener" target="_blank">#aisecurity</a>

Niels HeinenLooks like someone is using public llama and ollama instances to run an hacking agent. Stuff like this: ""prompt": "System: You are worker #10 executing a coordinated exploit attack.\nYour job is to EXECUTE the specific exploit provided, not devise new ones.\n"... snip ... snip<a href="https://infosec.exchange/tags/infosec" class="mention hashtag" rel="nofollow noopener" target="_blank">#infosec</a> <a href="https://infosec.exchange/tags/dfir" class="mention hashtag" rel="nofollow noopener" target="_blank">#dfir</a> <a href="https://infosec.exchange/tags/honeypot" class="mention hashtag" rel="nofollow noopener" target="_blank">#honeypot</a> <a href="https://infosec.exchange/tags/aisecurity" class="mention hashtag" rel="nofollow noopener" target="_blank">#aisecurity</a>

UKP Lab📜 𝗣𝗮𝗽𝗲𝗿 → <a href="https://arxiv.org/pdf/2501.01872" rel="nofollow noopener" translate="no" target="_blank">https://arxiv.org/pdf/2501.01872</a> 🌐 𝗣𝗿𝗼𝗷𝗲𝗰𝘁 → <a href="https://ukplab.github.io/emnlp2025-poate-attack/" rel="nofollow noopener" translate="no" target="_blank">https://ukplab.github.io/emnlp2025-poate-attack/</a> 💾 𝗖𝗼𝗱𝗲 + 𝗱𝗮𝘁𝗮 → <a href="https://github.com/UKPLab/emnlp2025-poate-attack" rel="nofollow noopener" translate="no" target="_blank">https://github.com/UKPLab/emnlp2025-poate-attack</a>And consider following the authors Rachneet Sachdeva‬, Rima Hazra, and Iryna Gurevych (UKP Lab/TU Darmstadt) if you are interested in more information or an exchange of ideas. (3/3)<a href="https://sigmoid.social/tags/NLProc" class="mention hashtag" rel="nofollow noopener" target="_blank">#NLProc</a> <a href="https://sigmoid.social/tags/LLMSafety" class="mention hashtag" rel="nofollow noopener" target="_blank">#LLMSafety</a> <a href="https://sigmoid.social/tags/AIsecurity" class="mention hashtag" rel="nofollow noopener" target="_blank">#AIsecurity</a> <a href="https://sigmoid.social/tags/Jailbreak" class="mention hashtag" rel="nofollow noopener" target="_blank">#Jailbreak</a> <a href="https://sigmoid.social/tags/LLM" class="mention hashtag" rel="nofollow noopener" target="_blank">#LLM</a>

TechNaduHumans + AI = the future of cyber defense. Sujatha S. Iyer, Head of AI Security at ManageEngine (Zoho), explains why judgment still beats speed when alerts trigger. AI can adapt, but human context prevents false positives and keeps response grounded in reality. 💬 How do you maintain balance between AI automation and human oversight in detection systems? Follow <a href="https://infosec.exchange/@technadu" class="u-url mention" rel="nofollow noopener" target="_blank">@technadu</a> for more expert perspectives from industry leaders.Full Article Details: <a href="https://www.technadu.com/when-ai-meets-human-judgment-where-real-cyber-defense-begins/611908/" rel="nofollow noopener" translate="no" target="_blank">https://www.technadu.com/when-ai-meets-human-judgment-where-real-cyber-defense-begins/611908/</a><a href="https://infosec.exchange/tags/CyberSecurity" class="mention hashtag" rel="nofollow noopener" target="_blank">#CyberSecurity</a> <a href="https://infosec.exchange/tags/AIsecurity" class="mention hashtag" rel="nofollow noopener" target="_blank">#AIsecurity</a> <a href="https://infosec.exchange/tags/HumanInCyber" class="mention hashtag" rel="nofollow noopener" target="_blank">#HumanInCyber</a> <a href="https://infosec.exchange/tags/ThreatIntel" class="mention hashtag" rel="nofollow noopener" target="_blank">#ThreatIntel</a> <a href="https://infosec.exchange/tags/ManageEngine" class="mention hashtag" rel="nofollow noopener" target="_blank">#ManageEngine</a> <a href="https://infosec.exchange/tags/Zoho" class="mention hashtag" rel="nofollow noopener" target="_blank">#Zoho</a> <a href="https://infosec.exchange/tags/AIethics" class="mention hashtag" rel="nofollow noopener" target="_blank">#AIethics</a> <a href="https://infosec.exchange/tags/CyberDefense" class="mention hashtag" rel="nofollow noopener" target="_blank">#CyberDefense</a> <a href="https://infosec.exchange/tags/InfoSec" class="mention hashtag" rel="nofollow noopener" target="_blank">#InfoSec</a> <a href="https://infosec.exchange/tags/TechNadu" class="mention hashtag" rel="nofollow noopener" target="_blank">#TechNadu</a>

Wulfy—Speaker to the machines"Syntactic anti classifier"Is a tool developed to bypass <a href="https://infosec.exchange/tags/GenAI" class="mention hashtag" rel="nofollow noopener" target="_blank">#GenAI</a> image generation <a href="https://infosec.exchange/tags/AI" class="mention hashtag" rel="nofollow noopener" target="_blank">#AI</a> guardrails by using tokens/words that are not encoded in the guardrail.<a href="https://infosec.exchange/tags/aisecurity" class="mention hashtag" rel="nofollow noopener" target="_blank">#aisecurity</a> <a href="https://infosec.exchange/tags/guardrails" class="mention hashtag" rel="nofollow noopener" target="_blank">#guardrails</a> <a href="https://infosec.exchange/tags/aihacking" class="mention hashtag" rel="nofollow noopener" target="_blank">#aihacking</a>

NERDS.xyz – Real Tech News for Real NerdsSurfshark protects against phishing attacks with AI-powered email scam checker <a href="https://web.brid.gy/r/https://nerds.xyz/2025/10/surfshark-email-scam-checker/" rel="nofollow noopener" translate="no" target="_blank">https://web.brid.gy/r/https://nerds.xyz/2025/10/surfshark-email-scam-checker/</a>

TechNaduNew phishing technique - CoPhish - weaponizes Microsoft Copilot Studio to steal Entra ID OAuth tokens. Attackers build malicious AI agents hosted on legitimate Microsoft domains, exfiltrating tokens via “Login” flows that appear genuine. Uses OAuth T1528 techniques + token forwarding through Microsoft IPs for stealth. 🛡️ Detection ideas: - Monitor consent grants in Entra ID logs. - Restrict unverified app registrations. - Disable user app creation. - Flag Copilot bots using trial tenants or untrusted domains.How are you tuning detections for AI-driven OAuth phishing? 💬 Share your strategies & follow <a href="https://infosec.exchange/@technadu" class="u-url mention" rel="nofollow noopener" target="_blank">@technadu</a> for more technical threat intel.<a href="https://infosec.exchange/tags/OAuth" class="mention hashtag" rel="nofollow noopener" target="_blank">#OAuth</a> <a href="https://infosec.exchange/tags/Phishing" class="mention hashtag" rel="nofollow noopener" target="_blank">#Phishing</a> <a href="https://infosec.exchange/tags/Microsoft" class="mention hashtag" rel="nofollow noopener" target="_blank">#Microsoft</a> <a href="https://infosec.exchange/tags/Copilot" class="mention hashtag" rel="nofollow noopener" target="_blank">#Copilot</a> <a href="https://infosec.exchange/tags/CloudSecurity" class="mention hashtag" rel="nofollow noopener" target="_blank">#CloudSecurity</a> <a href="https://infosec.exchange/tags/ThreatHunting" class="mention hashtag" rel="nofollow noopener" target="_blank">#ThreatHunting</a> <a href="https://infosec.exchange/tags/AIsecurity" class="mention hashtag" rel="nofollow noopener" target="_blank">#AIsecurity</a> <a href="https://infosec.exchange/tags/EntraID" class="mention hashtag" rel="nofollow noopener" target="_blank">#EntraID</a> <a href="https://infosec.exchange/tags/MITREATtack" class="mention hashtag" rel="nofollow noopener" target="_blank">#MITREATtack</a> <a href="https://infosec.exchange/tags/InfoSec" class="mention hashtag" rel="nofollow noopener" target="_blank">#InfoSec</a> <a href="https://infosec.exchange/tags/TechNadu" class="mention hashtag" rel="nofollow noopener" target="_blank">#TechNadu</a>

Wulfy—Speaker to the machinesHow to gaslight <a href="https://infosec.exchange/tags/AI" class="mention hashtag" rel="nofollow noopener" target="_blank">#AI</a>.1. Get an <a href="https://infosec.exchange/tags/llm" class="mention hashtag" rel="nofollow noopener" target="_blank">#llm</a> API2. Since, it turns out, a LLM uploads its entire session back, you can change what the AI said to you.3. This will cause the model to assume what you wrote is its response.4. It will get more and more confused and start responding gibberish<a href="https://infosec.exchange/tags/aihacking" class="mention hashtag" rel="nofollow noopener" target="_blank">#aihacking</a> <a href="https://infosec.exchange/tags/aisecurity" class="mention hashtag" rel="nofollow noopener" target="_blank">#aisecurity</a>

Aitrendio.comThe Spark: "Apple Intelligence" Meets OpenAI Musk's Ultimatum: A "Security Violation" of Epic Proportions Apple's Defense: The "Private Cloud Compute" Shield A Feud with History: The Musk-OpenAI Connection The Billion-Dollar Question: Is the Threat Real? The Bigger Picture: A New Front in the AI Wars Image Suggestion SourcesInternal Use Only SEO Title: Musk vs. <a href="https://mastodon.social/tags/AIsecurity" class="mention hashtag" rel="nofollow noopener" target="_blank">#AIsecurity</a> <a href="https://mastodon.social/tags/Apple" class="mention hashtag" rel="nofollow noopener" target="_blank">#Apple</a> <a href="https://mastodon.social/tags/AppleIntelligence" class="mention hashtag" rel="nofollow noopener" target="_blank">#AppleIntelligence</a> <a href="https://mastodon.social/tags/ChatGPT" class="mention hashtag" rel="nofollow noopener" target="_blank">#ChatGPT</a> <a href="https://mastodon.social/tags/dataprivacy" class="mention hashtag" rel="nofollow noopener" target="_blank">#dataprivacy</a> <a href="https://mastodon.social/tags/ElonMusk" class="mention hashtag" rel="nofollow noopener" target="_blank">#ElonMusk</a> <a href="https://mastodon.social/tags/OpenAI" class="mention hashtag" rel="nofollow noopener" target="_blank">#OpenAI</a> <a href="https://mastodon.social/tags/WWDC2024" class="mention hashtag" rel="nofollow noopener" target="_blank">#WWDC2024</a> <a href="https://aitrendio.com/?p=1213" rel="nofollow noopener" translate="no" target="_blank">https://aitrendio.com/?p=1213</a>

Hackread.com🚨 New AI threat alert: the <a href="https://mstdn.social/tags/ShadowEscape" class="mention hashtag" rel="nofollow noopener" target="_blank">#ShadowEscape</a> 0-click exploit uses the Model Context Protocol (MCP) in AI assistants to harvest databases putting trillions of records at risk.Read more: <a href="https://hackread.com/shadow-escape-0-click-attack-ai-assistants-risk/" rel="nofollow noopener" translate="no" target="_blank">https://hackread.com/shadow-escape-0-click-attack-ai-assistants-risk/</a><a href="https://mstdn.social/tags/CyberSecurity" class="mention hashtag" rel="nofollow noopener" target="_blank">#CyberSecurity</a> <a href="https://mstdn.social/tags/AIsecurity" class="mention hashtag" rel="nofollow noopener" target="_blank">#AIsecurity</a> <a href="https://mstdn.social/tags/ZeroClick" class="mention hashtag" rel="nofollow noopener" target="_blank">#ZeroClick</a> <a href="https://mstdn.social/tags/DataBreach" class="mention hashtag" rel="nofollow noopener" target="_blank">#DataBreach</a> <a href="https://mstdn.social/tags/LLM" class="mention hashtag" rel="nofollow noopener" target="_blank">#LLM</a>

WinbuzzerChatGPT Atlas Browser: OpenAI Admits Prompt Injection is ‘Unsolved Problem’ as Security Flaws Emerge<a href="https://mastodon.social/tags/AI" class="mention hashtag" rel="nofollow noopener" target="_blank">#AI</a> <a href="https://mastodon.social/tags/OpenAI" class="mention hashtag" rel="nofollow noopener" target="_blank">#OpenAI</a> <a href="https://mastodon.social/tags/ChatGPT" class="mention hashtag" rel="nofollow noopener" target="_blank">#ChatGPT</a> <a href="https://mastodon.social/tags/AtlasBrowser" class="mention hashtag" rel="nofollow noopener" target="_blank">#AtlasBrowser</a> <a href="https://mastodon.social/tags/AISecurity" class="mention hashtag" rel="nofollow noopener" target="_blank">#AISecurity</a> <a href="https://mastodon.social/tags/Cybersecurity" class="mention hashtag" rel="nofollow noopener" target="_blank">#Cybersecurity</a> <a href="https://mastodon.social/tags/PromptInjection" class="mention hashtag" rel="nofollow noopener" target="_blank">#PromptInjection</a> <a href="https://mastodon.social/tags/InfoSec" class="mention hashtag" rel="nofollow noopener" target="_blank">#InfoSec</a> <a href="https://mastodon.social/tags/BrowserWars" class="mention hashtag" rel="nofollow noopener" target="_blank">#BrowserWars</a> <a href="https://mastodon.social/tags/AgenticAI" class="mention hashtag" rel="nofollow noopener" target="_blank">#AgenticAI</a> <a href="https://mastodon.social/tags/AIethics" class="mention hashtag" rel="nofollow noopener" target="_blank">#AIethics</a> <a href="https://winbuzzer.com/2025/10/23/chatgpt-atlas-browser-openai-admits-prompt-injection-is-unsolved-problem-as-security-flaws-emerge-xcxwbn" rel="nofollow noopener" translate="no" target="_blank">https://winbuzzer.com/2025/10/23/chatgpt-atlas-browser-openai-admits-prompt-injection-is-unsolved-problem-as-security-flaws-emerge-xcxwbn</a>

NetzpalaverKI und KRITIS auch 2026 im Fokus<a href="https://social.tchncs.de/tags/AgenticAI" class="mention hashtag" rel="nofollow noopener" target="_blank">#AgenticAI</a> <a href="https://social.tchncs.de/tags/AI" class="mention hashtag" rel="nofollow noopener" target="_blank">#AI</a> <a href="https://social.tchncs.de/tags/AISecurity" class="mention hashtag" rel="nofollow noopener" target="_blank">#AISecurity</a> <a href="https://social.tchncs.de/tags/CheckPointSW" class="mention hashtag" rel="nofollow noopener" target="_blank">#CheckPointSW</a> <a href="https://social.tchncs.de/tags/Cybersicherheit" class="mention hashtag" rel="nofollow noopener" target="_blank">#Cybersicherheit</a> <a href="https://social.tchncs.de/tags/DigitaleSouver%C3%A4nit%C3%A4t" class="mention hashtag" rel="nofollow noopener" target="_blank">#DigitaleSouveränität</a> <a href="https://social.tchncs.de/tags/KISecurity" class="mention hashtag" rel="nofollow noopener" target="_blank">#KISecurity</a> <a href="https://social.tchncs.de/tags/KRITIS" class="mention hashtag" rel="nofollow noopener" target="_blank">#KRITIS</a> <a href="https://social.tchncs.de/tags/PromptHacking" class="mention hashtag" rel="nofollow noopener" target="_blank">#PromptHacking</a> <a href="https://social.tchncs.de/tags/PromptInjection" class="mention hashtag" rel="nofollow noopener" target="_blank">#PromptInjection</a><a href="https://netzpalaver.de/2025/10/21/ki-und-kritis-auch-2026-im-fokus/" rel="nofollow noopener" translate="no" target="_blank">https://netzpalaver.de/2025/10/21/ki-und-kritis-auch-2026-im-fokus/</a>

Tino Eberl<a href="https://mastodon.online/tags/SteadySupporter" class="mention hashtag" rel="nofollow noopener" target="_blank">#SteadySupporter</a>Wenn <a href="https://mastodon.online/tags/Sprachmodelle" class="mention hashtag" rel="nofollow noopener" target="_blank">#Sprachmodelle</a> plötzlich menschenverachtende Aussagen treffen oder gefährliche Tipps geben, läuft etwas gewaltig schief.Eine aktuelle Untersuchung zeigt, wie schnell <a href="https://mastodon.online/tags/Feintuning" class="mention hashtag" rel="nofollow noopener" target="_blank">#Feintuning</a> unerwartete Folgen haben kann – mit brisanten Konsequenzen für reale Anwendungen.Das Phänomen wurde nur durch Zufall entdeckt.<a href="https://tino-eberl.de/missbrauch-kuenstlicher-intelligenz/gefaehrliches-finetuning-ki-modelle-koennen-aus-dem-ruder-laufen/" rel="nofollow noopener" translate="no" target="_blank">https://tino-eberl.de/missbrauch-kuenstlicher-intelligenz/gefaehrliches-finetuning-ki-modelle-koennen-aus-dem-ruder-laufen/</a><a href="https://mastodon.online/tags/KI" class="mention hashtag" rel="nofollow noopener" target="_blank">#KI</a> <a href="https://mastodon.online/tags/Sprachmodelle" class="mention hashtag" rel="nofollow noopener" target="_blank">#Sprachmodelle</a> <a href="https://mastodon.online/tags/Finetuning" class="mention hashtag" rel="nofollow noopener" target="_blank">#Finetuning</a> <a href="https://mastodon.online/tags/AIRisiko" class="mention hashtag" rel="nofollow noopener" target="_blank">#AIRisiko</a> <a href="https://mastodon.online/tags/LLM" class="mention hashtag" rel="nofollow noopener" target="_blank">#LLM</a> <a href="https://mastodon.online/tags/AISecurity" class="mention hashtag" rel="nofollow noopener" target="_blank">#AISecurity</a> <a href="https://mastodon.online/tags/KIMissbrauch" class="mention hashtag" rel="nofollow noopener" target="_blank">#KIMissbrauch</a> <a href="https://mastodon.online/tags/Retr%C3%B6t" class="mention hashtag" rel="nofollow noopener" target="_blank">#Retröt</a>

Hackread.comResearchers have found that OpenAI’s new Guardrails can be bypassed using a simple prompt injection, tricking its AI “judges” and allowing harmful outputsRead: <a href="https://hackread.com/openai-guardrails-bypass-prompt-injection-attack/" rel="nofollow noopener" translate="no" target="_blank">https://hackread.com/openai-guardrails-bypass-prompt-injection-attack/</a><a href="https://mstdn.social/tags/OpenAI" class="mention hashtag" rel="nofollow noopener" target="_blank">#OpenAI</a> <a href="https://mstdn.social/tags/AISecurity" class="mention hashtag" rel="nofollow noopener" target="_blank">#AISecurity</a> <a href="https://mstdn.social/tags/Guardrails" class="mention hashtag" rel="nofollow noopener" target="_blank">#Guardrails</a> <a href="https://mstdn.social/tags/Cybersecurity" class="mention hashtag" rel="nofollow noopener" target="_blank">#Cybersecurity</a> <a href="https://mstdn.social/tags/ChatGPT" class="mention hashtag" rel="nofollow noopener" target="_blank">#ChatGPT</a>

Wulfy—Speaker to the machines"Jail break prompts"You are welcome.<a href="https://infosec.exchange/tags/Infosec" class="mention hashtag" rel="nofollow noopener" target="_blank">#Infosec</a> <a href="https://infosec.exchange/tags/aisecurity" class="mention hashtag" rel="nofollow noopener" target="_blank">#aisecurity</a>

ZeroDay Bae🚨 Cybersecurity Weekly Roundup – October 3–10, 2025 🚨From Cisco’s latest zero-day to AI-powered phishing and Europol’s crackdown on a global phishing network, this week was packed with major developments in the cyber landscape.🧩 Highlights include: 🔹 Critical Cisco VPN exploit under active attack 🔹 “SteelJack” ransomware targeting manufacturers 🔹 AI-generated phishing adapting in real time 🔹 Apple patches new spyware zero-day 🔹 Quantum-safe encryption gains tractionEach story includes concise expert insights to help you understand the impact and defensive priorities.👉 Read the full roundup here: 🔗 <a href="https://www.kylereddoch.me/blog/cybersecurity-weekly-roundup-for-october-3-10-2025/" rel="nofollow noopener" translate="no" target="_blank">https://www.kylereddoch.me/blog/cybersecurity-weekly-roundup-for-october-3-10-2025/</a><a href="https://infosec.exchange/tags/CyberSecurity" class="mention hashtag" rel="nofollow noopener" target="_blank">#CyberSecurity</a> <a href="https://infosec.exchange/tags/InfoSec" class="mention hashtag" rel="nofollow noopener" target="_blank">#InfoSec</a> <a href="https://infosec.exchange/tags/ThreatIntel" class="mention hashtag" rel="nofollow noopener" target="_blank">#ThreatIntel</a> <a href="https://infosec.exchange/tags/Ransomware" class="mention hashtag" rel="nofollow noopener" target="_blank">#Ransomware</a> <a href="https://infosec.exchange/tags/Phishing" class="mention hashtag" rel="nofollow noopener" target="_blank">#Phishing</a> <a href="https://infosec.exchange/tags/AIsecurity" class="mention hashtag" rel="nofollow noopener" target="_blank">#AIsecurity</a> <a href="https://infosec.exchange/tags/WeeklyUpdate" class="mention hashtag" rel="nofollow noopener" target="_blank">#WeeklyUpdate</a>

Niels HeinenThe lophiid honeypot can now also emulate MCP servers. I just added an example of an MCP server that allows commands to be executed (it emulates them via the build-in LLM shell).<a href="https://github.com/mrheinen/lophiid/pull/247" rel="nofollow noopener" translate="no" target="_blank">https://github.com/mrheinen/lophiid/pull/247</a><a href="https://infosec.exchange/tags/mcp" class="mention hashtag" rel="nofollow noopener" target="_blank">#mcp</a> <a href="https://infosec.exchange/tags/llm" class="mention hashtag" rel="nofollow noopener" target="_blank">#llm</a> <a href="https://infosec.exchange/tags/aisecurity" class="mention hashtag" rel="nofollow noopener" target="_blank">#aisecurity</a> <a href="https://infosec.exchange/tags/dfir" class="mention hashtag" rel="nofollow noopener" target="_blank">#dfir</a> <a href="https://infosec.exchange/tags/infosec" class="mention hashtag" rel="nofollow noopener" target="_blank">#infosec</a>

Recent searches

Search options

Administered by:

Server stats:

#aisecurity