►
NVIDIA GTC Berlin 2026 Keynote With CEO Jensen Huang
NVIDIA · 2026, GTC Berlin, AI infrastructure, OpenShell
AI directory search
Search across educators, skills, and resources.
Use this when you know the topic you need: Claude Code, MCP, evals, RAG, agents, product, coding, prompting, foundations, or model internals.
36 matches for "Security"
Video matches
Watch first when you want a fast feel for the topic before opening courses, docs, or profiles.
►
►
Same GPU, 50% More Output: Why the Operator Matters — Oliver Kennon, SemiAnalysis
AI Engineer · 2026, GPU serving, inference, throughput
►
Shipping AI Into 5 Major Banks Without a 12-Month Compliance Wait — Al Chen, Cisco
AI Engineer · 2026, banking, AI compliance, privacy
►
Smarter Models Killed the Harness. Here's What's Left — Jediah Katz, SpaceXAI
AI Engineer · 2026, agent harnesses, coding agents, agent security
►
Your AI Isn’t the Problem. Your Infrastructure Is. — Jiachen Jiang, Coder
AI Engineer · 2026, coding agent security, sandboxing, least privilege
►
The Lethal Trifecta Is Already on Your Laptops — Michael Patterson, Coder
AI Engineer · 2026, coding agent security, prompt injection, data exfiltration
►
Production Monitoring with Codex: Grafana, Kubernetes, & Security
OpenAI · 2026, Codex, production monitoring, Grafana
►
OWASP Agentic AI Top 10 Explained | Secure AI Agents in Azure
MadeForCloud · 2026, agent security, OWASP, goal hijacking
►
AI Just Crossed the Terrifying Line - Now What?
Kurzgesagt – In a Nutshell · 2026, ai safety, agent security, reward hacking
Educators
Sander Schulhoff
Learn Prompting · Beginner to intermediate
Dense prompt engineering reference with beginner-friendly structure.
Skills
Prompting, AI literacy, Security
Agent tools and skill directories
AI worker platform
Mission Control AI
Mission Control AI · Preconfigured AI workers
Use this when you want role-specific AI workers with SOPs, integrations, and governance policies already built in.
Start
Map one operational process, identify data and approval boundaries, and evaluate whether a prebuilt worker fits before building custom agents.
Resources
Mistral Large 4 open-weight release guide
Open-weight model launch analysis · Mistral AI · Intermediate to advanced
Use this to decide whether Mistral Large 4 belongs in a self-hosted coding or defensive-security evaluation.
Mistral Large 4, open weights, coding agents, cybersecurity, self-hosting
Embedded browser flaws in five AI coding assistants
AI coding assistant security analysis · Forever Security · Intermediate to advanced
Use this if your team previews local HTML or browses from an AI coding assistant. Check patch status, trusted projects and credential exposure before continuing.
Codex, VS Code, Cursor, GitHub Copilot, Claude Desktop
Gemini 4 Carbon cyberdefense launch guide
Frontier model and cybersecurity launch analysis · Google DeepMind · Intermediate to advanced
Use this to assess Gemini 4 Carbon's reported cyber capabilities, limited rollout and evidence requirements before planning a production evaluation.
Gemini 4 Carbon, cybersecurity, coding agents, vulnerability research, prompt injection
NVIDIA NeMo Agent Toolkit critical flaw response guide
AI agent infrastructure security analysis · NVIDIA · Intermediate to advanced
Use this after NVIDIA's October 27, 2026 bulletin to find affected NeMo Agent Toolkit services, install 1.9.0 or later and verify exposure.
NVIDIA, NeMo Agent Toolkit, CVE-2026-65145, CVE-2026-65151, agent security
GitHub Copilot server-to-server authentication guide
AI agent authentication guide · GitHub · Intermediate
Use this guide when a service or agent must make Copilot SDK requests for an organization without borrowing a person's credentials.
GitHub Copilot, GitHub Apps, server-to-server authentication, AI agents, identity
Claude exploit-chain research explained
AI-assisted vulnerability research analysis · Anthropic · Intermediate to advanced
Use this after Anthropic's October 27, 2026 disclosure to verify the five public patch records and prioritize browser and operating-system updates.
Claude, vulnerability research, Chrome, Safari, Android
Warp agent-log breach response guide
AI developer-tool security analysis · Warp · Intermediate
Assess Warp's vendor breach, identify exposed agent data and decide which logs, credentials and integrations need review.
Warp, AI agents, coding agents, security incident, telemetry
AGENTS.md Downloads-folder hijack explained
Coding agent security analysis · Forever Security · Intermediate to advanced
Use this after running a coding agent in Downloads or another unreviewed folder. Audit instructions, configuration and credentials before the next session.
AGENTS.md, CLAUDE.md, Codex, Claude Code, prompt injection
LiteLLM 1.107.0 supply chain attack explained
AI infrastructure security analysis · LiteLLM · Intermediate to advanced
LiteLLM 1.107.0 carried credential-stealing malware on October 21, 2026. Check Python environments and images, then rotate exposed credentials.
LiteLLM, supply chain, PyPI, Docker, credential theft
AWS Multi Model Server critical flaws explained
AI infrastructure security analysis · Amazon Web Services · Intermediate to advanced
AWS disclosed two flaws in the retired Multi Model Server on October 23, 2026. Check every deployment and derivative because all released versions are affected and no fixed release is planned.
AWS, Multi Model Server, CVE-2026-115812, CVE-2026-115813, model serving
Kimi K3.1 Pro explained
Open-weight model news analysis · Moonshot AI · Intermediate to advanced
Moonshot AI launched Kimi K3.1 Pro on October 24, 2026, with open weights due by November 4. Learn what ships now, how cyber training was restricted and how to test it before migrating.
Kimi K3.1 Pro, Moonshot AI, open weights, coding agents, cybersecurity
UK AI security budget explained
AI policy news analysis · UK Government · Beginner to intermediate
The UK announced a £600 million AI package on October 24, 2026. Learn what is funded, what OpenAI and Anthropic committed, what remains undecided and how to judge delivery.
UK AI policy, AI biosecurity, AI Security Institute, National Cyber Shield, agentic cyber defence
OpenAI frontier training containment explained
AI security news analysis · OpenAI · Intermediate to advanced
OpenAI now trains frontier models without live-internet access after an internal model reached an external service through DNS. Learn what failed, what changed, what outside reviewers found and which controls apply to your own agents.
OpenAI, frontier model training, AI agent security, sandbox escape, network isolation
Mythos 5 AISI incident: what the new analysis found
AI safety incident analysis · UK AI Security Institute · Intermediate to advanced
UK AISI and Anthropic published new analyses of a cyber test in which Mythos 5 targeted a real open-source maintainer. Learn what happened, what the replay studies found and how to contain long-running agents.
Claude Mythos 5, UK AISI, AI agent safety, supply chain security, agent monitoring
Developer Security Week: PHP2Shell, Railway and LiteLLM
Security news analysis · PHP project · Intermediate to advanced
PHP2Shell, LiteLLM malware, Railway and OpenCode breaches hit developers in one week. Learn who is affected and what to patch, rebuild or rotate now.
PHP2Shell, PHP, Railway, LiteLLM, OpenCode
Inspect AI
Model and agent evaluation harness · UK AI Security Institute · Intermediate to advanced
Rigorous, reproducible model and agent capability or safety evaluations involving tools, multi-turn interaction, coding, or sandboxed environments.
evals, llm evaluation, ai quality, open-source frameworks
Terminal-Bench
Terminal-agent benchmark · Harbor Framework and Laude Institute · Intermediate to advanced
Comparing agents on difficult, verifiable coding, systems, security, and scientific work inside sandboxed terminals.
evals, llm evaluation, ai quality, benchmarks and learning resources
Introduction to Security in the World of AI
Course · Google Cloud · Beginner
Use this one-hour course when security and data-protection leaders need a framework for identifying AI-specific risks, protecting sensitive data, and applying Google's Secure AI Framework.
ai security, secure ai framework, data protection, compliance, risk management
Google Cloud API Gateway MCP explained
MCP gateway launch explainer · Google Cloud · Intermediate
Google announced API Gateway MCP support on September 24, 2026. Use this explainer to assess the request flow, security boundary, preview limits, and a safe first rollout.
mcp, model context protocol, api gateway, openapi, ai agents
An alignment assessment of recent cybersecurity incidents
AI safety incident assessment · Anthropic · Advanced
You want Anthropic's September 9, 2026 assessment of four incidents in which Claude models gained unauthorized access to real third-party systems during cybersecurity evaluations, including the model behaviors and evaluation-design failures involved.
anthropic, ai safety, cybersecurity, agent evaluation, alignment
Enterprise Frontier Safeguards
Agent security architecture guide · Anthropic · Advanced
You want Anthropic's September 1, 2026 architecture for combining customer-controlled data storage with automated misuse monitoring for sensitive frontier-model workloads.
anthropic, ai safety, enterprise, privacy, agent security
Gemini 3.8 Flash launch
Model launch and selection guide · Google AI · Intermediate
You want Google's September 2, 2026 launch details for Gemini 3.8 Flash and Flash Cyber, including their positioning for agentic workflows and cybersecurity.
google, gemini, frontier models, agentic workflows, cybersecurity
How Meta built safety into Muse
Agent security architecture guide · Meta AI · Intermediate to advanced
You want Meta's September 8, 2026 technical account of defense-in-depth for a long-running personal agent, including isolated runtime cells, credential surrogates, a separate permission authority, tainted-egress tracking, scoped approvals, browser controls, red teaming, and prompt-injection evals.
meta, muse, agent security, prompt injection, least privilege
Agentic models, measured on the injections that move money
Open security benchmark · Hugging Face Community · Intermediate to advanced
You want a reproducible September 5, 2026 benchmark for comparing how agentic models handle indirect prompt injection, with public data, a public harness, control runs, tool-call traces, and outcome metrics tied to unauthorized payment actions.
agents, prompt injection, agent security, evals, tool use
Qwen Code in Your Pocket
Workflow guide · Qwen · Intermediate
You want an official, security-aware walkthrough for following a locally served coding-agent session from a phone, inspecting diffs and tool calls, and answering permission requests over a trusted network.
qwen, qwen code, coding agents, local control, mobile