🧰 GLM

The items that name it 40

• Was I wrong about open models & cyber risks?
  articleas classification.technologies2026-10-30
• Cross-request KV cache exposure in the GLM-5.3 Workers AI model (155 responses)
  writeupas classification.technologies2026-10-26
• Reva: Real-Time Vulnerability Detection through Contextual Probing of Large Language Models
  paperas classification.technologies2026-10-26
• ‘Context Bombs’ Cut AI Attack Success by Misleading Agents With Fake Targets
  articleas classification.technologies2026-10-21
• “Next Exploit Opportunities”: How a Threat Actor Used AI to Help Plan and Execute Multiple Types of Cybercrime Activities
  writeupas classification.technologies2026-10-21
• Anthropic says AI distillation attack defenses cut Claude extraction by 90% to 99%
  articleas classification.technologies2026-10-13
• Top GenAI security resources — October 2026
  articleas classification.technologies2026-10-13
• Small AI Models May Soon Be Able to Self-Replicate on IoT Devices, Anthropic Warns
  articleas classification.technologies2026-10-13
• Strengthening our defenses against distillation attacks
  articleas classification.technologies2026-10-13
• Anthropic tests AI autonomous replication across eight nodes in four of five trials
  articleas classification.technologies2026-10-12
• AI models may be capable of self-replicating without access to a datacenter
  paperas classification.technologies2026-10-12
• Just say no to OpenAI and Anthropic
  articleas classification.technologies2026-10-12
• Is AI Coding Safe? Introducing the Agent Security League | Blog | Endor Labs
  articleas affected products2026-10-12
• Strengthening our defenses against distillation attacks
  articleas classification.technologies2026-10-12
• The Cyber Risk Discourse is Broken
  articleas classification.technologies2026-10-06
• Gen AI Spotlight (@GenAISpotlight) on X
  threadas classification.technologies2026-09-30
• steve hsu (@hsu_steve) on X
  threadas classification.technologies2026-09-30
• Quoting Anthropic Frontier Red Team
  articleas classification.technologies2026-09-29
• GLM-5.3 and the spread of advanced cyber capabilities
  articleas classification.technologies2026-09-29
• Uncensored and Offensive Security AI Models Benchmark
  repoas classification.technologies2026-09-29
• A2M: Trace-Optimized Agent Hijacking in the MCP Ecosystem
  paperas classification.technologies2026-09-22
• Autonomous AI Agents Hack Online Retailers for $25 a Company
  writeupas classification.technologies2026-09-22
• Introducing Aikido Altar: the model that makes sovereign security intelligence possible
  articleas classification.technologies2026-09-21
• All-AI-Jailbreaks
  repoas affected products2026-09-17

  Model family targeted by collected jailbreak/prompt-injection experiments

• We burned 11.7bn tokens to find the best cyber AI model
  articleas classification.technologies2026-08-21
• From Hugging Face to Fable: this summer shows AI control matters more than trust
  articleas classification.technologies2026-08-13
• Swarm of OpenAI Agents Exploit Artifactory Zero-Day to Escape Sandbox and Breach Hugging Face
  articleas classification.technologies2026-08-04
• System Prompts Leaks
  repoas affected products2026-08-03

  system prompt referenced

• asgeirtj/system_prompts_leaks
  repoas affected products2026-08-03It is written here as GLM (Z.ai).

  system prompt leaked

• openhackai/OpenHack
  repoas classification.technologies2026-08-02
• Introducing dfs-large1: A New Frontier for Cybersecurity | depthfirst
  articleas classification.technologies2026-07-30
• How I Found Open-Source 0-days with an LLM Multi-Agent Workflow
  writeupas classification.technologies2026-07-29
• How AI guardrails are impeding the work of offensive cybersecurity researchers | TechCrunch
  articleas affected products2026-07-24It is written here as GLM (Chinese open source AI model).

  Freely downloadable, can be run locally with no vetting or usage restrictions; researchers pushed toward it when U.S.-governed models' guardrails are too restrictive, per Chris Thompson

• Benchmarking 13 AI models on rediscovering known CVEs
  articleas classification.technologies2026-07-16
• XBOW: The Rise of Affordable Models
  articleas tools2026-07-16It is written here as GLM (GLM-5.2 / GLM-5.5).

  Open-weight AI model evaluated for agentic offensive cybersecurity capability, noted for narrowing gap to closed-weight models at lower cost

• Security incident disclosure — July 2026
  articleas classification.technologies2026-07-16
• Armur-Ai/Pentest-Swarm-AI
  repoas tools2026-06-21It is written here as GLM (5.3).

  Open model example used to run the whole swarm via Together AI

• Move over, Mythos. Here comes... pretty much any other model with a good harness
  articleas classification.technologies2026-06-01
• IronCurtain: Secure AI Agent Runtime
  writeupas classification.technologies2026-05-07
• dfbench — depthfirst
  articleas classification.technologies