★ NO REAL MONEY ★ INTEL: The new HTB Certified Offensive AI Expert (HTB CO-AE) is officially here ◆ INTEL: Improving Fable 5's biology safeguards - Anthropic ◆ Will itspricedin.lol itself get pwned within 90 days of launch? — YES 99.1% ◆ Will a major password manager disclose a CVSS 9.0+ vulnerability befor — NO 60.0% ◆ Will a global Cloudflare, AWS, or Azure outage lasting over 3 hours be — YES 55.0% ◆ Will a leaked system prompt lead to a public apology from a major AI l — NO 70.0% ◆ Will a jailbreak prompt sell as an NFT for more than 1 ETH before 2027 — NO 95.0% ◆ Will a prompt injection attack be publicly blamed for a data breach at — YES 62.0% ◆ Will an AI browser agent be shown exfiltrating user data via prompt in — YES 70.0% ◆ Will $POC ever be worth anything? — NO 99.9% ◆ INTEL: Free LLM-based Vulnerability Scans for Open Source Projects ◆ INTEL: Daniel Miessler on how Meta and Microsoft damaged themselves with incoherent AI ◆ INTEL: Infrastructure patterns for agentic applications ◆ Will an executive literally say 'it's priced in' about a breach on an — NO 85.0% ◆ INTEL: Thoughts on slowing the fuck down - how we should work with coding agents ◆ Which AI lab discloses the next headline security incident? — OpenAI 46.2% ◆ INTEL: Peter Winter-Smith announces wSAST, a code analyser for application security con ◆ Will AI-generated bug reports cause a major open-source project to shu — YES 55.0% ◆ Will a CVSS 9.0+ RCE be disclosed in a major AI coding agent before 20 — YES 80.5% ◆ INTEL: The Right Way to Embed an LLM in a Group Chat ◆ ★ $POC HAS NO VALUE ★ ◆
🕵️ Intel feed — 5660 resources from the ai-security compendium
Clear

Categories: Agent Frameworks · Agent Identity · Agent Security · Anti-Crawling · Architecture · Benchmarks · Code Analysis · Coding Tools · Detection and Monitoring · Engineering Patterns · Frameworks and Standards · General Reading · Governance and Policy · Guardrails and Firewalls · Honeypots and Deception · Incidents · Jailbreaking · MCP (Model Context Protocol) · Model Attacks · Papers · Privacy · Prompt Injection · Red Teaming · Safety and Alignment · Sandboxing and Isolation · Secrets Management · Secure Coding · Supply Chain · Threat Modeling

Showing 71 of 71. Source: github.com/AnthonyHerman/ai-security-corpus · browse it in Internet Explorer. This is the research; the markets are the bets.

Snapshot 2026-10-10 · last checked 2026-10-13 14:25 UTC · NEW = added in the last 14 days (nothing fresh this fortnight; the bugs are resting)

TitleCategorySection
Secure, kernel-enforced sandbox CLI aSandboxing and IsolationSandbox Tools
OpenSandbox is a general-purpose sandSandboxing and IsolationSandbox Tools
Python read-only sandbox for LLM agents anSandboxing and IsolationSandbox Tools
A minimal, secure Python interpreter writtSandboxing and IsolationSandbox Tools
Postgres SandboxSandboxing and IsolationSandbox Tools
Claude "File creation" is actually a sandboxed code execution environment and hasSandboxing and IsolationSandbox Tools
acl-proxy - Rust ACL-aware HTTP/HTTPS proxy with URL policy engineSandboxing and IsolationSandbox Tools
Agent Safehouse - macOS kernel-level sandboxing for LLM coding agentsSandboxing and IsolationSandbox Tools
Box by ASCII - cheap persistent Linux VM sandboxes for AI agentsSandboxing and IsolationSandbox Tools
Bromure - disposable Linux VM sandboxes on macOS for AI coding agents and browsingSandboxing and IsolationSandbox Tools
clawker - self-hosted AI coding agent sandbox in Docker with egress firewallSandboxing and IsolationSandbox Tools
cloudflare/computer - virtual filesystem and sandboxed execution environment for agentsSandboxing and IsolationSandbox Tools
Coder - self-hosted, governed environments for running AI coding agents at scaleSandboxing and IsolationSandbox Tools
Cordium - open-source identity-based sandbox platform for developers and AI agentsSandboxing and IsolationSandbox Tools
CubeSandbox - secure lightweight sandbox for AI agentsSandboxing and IsolationSandbox Tools
Dan Guido on running Claude Code in YOLO mode safely with the Trail of Bits devcontainerSandboxing and IsolationSandbox Tools
Daytona - Secure Infrastructure for Running AI-Generated CodeSandboxing and IsolationSandbox Tools
Docker Sandboxes - Run Claude Code and Coding Agents Unsupervised but SafelySandboxing and IsolationSandbox Tools
dyana - sandbox for loading, running and profiling ML models, pickles and other filesSandboxing and IsolationSandbox Tools
exe.dev - disposable sandbox VMs for AI agentsSandboxing and IsolationSandbox Tools
fend - sandboxed micro-VM runtime for npm install and dev scriptsSandboxing and IsolationSandbox Tools
hazmat - OS-level containment for AI coding agentsSandboxing and IsolationSandbox Tools
httpjail - HTTP and HTTPS request filter and network isolation for processesSandboxing and IsolationSandbox Tools
iron-proxy v0.23.0 - egress firewall for untrusted workloadsSandboxing and IsolationSandbox Tools
jailer - eBPF-based mandatory access control process jailing for LinuxSandboxing and IsolationSandbox Tools
John McBride introduces stereOS, a hardened NixOS-based operating system for sandboxing AI agentsSandboxing and IsolationSandbox Tools
Landlock - unprivileged sandboxing for LinuxSandboxing and IsolationSandbox Tools
Lume - macOS VM sandbox for AI agentsSandboxing and IsolationSandbox Tools
mezz - self-contained wifi sandbox for inspecting IoT devicesSandboxing and IsolationSandbox Tools
MXC - Microsoft eXecution Container for sandboxing untrusted model output and toolsSandboxing and IsolationSandbox Tools
netfence - eBPF network egress allowlisting daemon for VMs and containersSandboxing and IsolationSandbox Tools
sandbox-probe - agentic sandbox enumeration and escape testing for AI coding agentsSandboxing and IsolationSandbox Tools
sandcat - Docker dev container sandbox for AI agents with mitmproxy network rules and secret injectionSandboxing and IsolationSandbox Tools
shuru - local-first microVM sandbox for AI agentsSandboxing and IsolationSandbox Tools
SlicerVM - real Linux microVMs for AI sandboxesSandboxing and IsolationSandbox Tools
traffico - eBPF traffic shaping with network intent guardrails for agent workloadsSandboxing and IsolationSandbox Tools
vmux - stateful sandboxes for agentsSandboxing and IsolationSandbox Tools
yolobox - sandboxed AI coding agents in a containerSandboxing and IsolationSandbox Tools
Docker Desktop 4.40 Release - DockerSandboxing and IsolationContainerization
Docker Labs: GenAI No. 19Sandboxing and IsolationContainerization
Containerize your agents!Sandboxing and IsolationContainerization
Docker Sandboxes: Run Agents in YOLO Mode, SafelySandboxing and IsolationContainerization
Docker SandboxesSandboxing and IsolationContainerization
Chainguard Images - minimal hardened container imagesSandboxing and IsolationContainerization
Chainguard OS WhitepaperSandboxing and IsolationContainerization
Containerize your agents! - DaggerSandboxing and IsolationContainerization
Copacetic - directly patch container image vulnerabilitiesSandboxing and IsolationContainerization
Copy Fail in Kubernetes: RuntimeDefault Did Not Block AF_ALG - CVE-2026-31431Sandboxing and IsolationContainerization
Docker-OSX - run macOS in Docker for security researchSandboxing and IsolationContainerization
Greg Castle on converting GKE system containers to non-root - KubeCon EU talk summarySandboxing and IsolationContainerization
Kasm Workspaces - container streaming and remote browser isolationSandboxing and IsolationContainerization
Kubernetes security: Safeguarding your container kingdom - Red CanarySandboxing and IsolationContainerization
macOS Containers Initiative - native container support and isolation on macOSSandboxing and IsolationContainerization
Minimus - free hardened container images with near-zero CVEsSandboxing and IsolationContainerization
oci-seccomp-bpf-hook - OCI hook to trace syscalls and generate seccomp profilesSandboxing and IsolationContainerization
Orchard - native macOS UI for Apple Containers with sandboxed agentsSandboxing and IsolationContainerization
seccomp-profiler - eBPF tool that generates per-container seccomp profilesSandboxing and IsolationContainerization
Securing the Container World with Policies: acjs and ctrdacSandboxing and IsolationContainerization
tank-os - Fedora bootc image for running OpenClaw as a rootless Podman workloadSandboxing and IsolationContainerization
YOLO in the Sandbox – VoratiqSandboxing and IsolationGuides and Discussion
KiloClaw Security White PaperSandboxing and IsolationGuides and Discussion
A field guide to sandboxes for AISandboxing and IsolationGuides and Discussion
Agent Safety is a Box - Marc BrookerSandboxing and IsolationGuides and Discussion
Daniel Von Fange on secure crypto dev needing 4 isolated computers - no npm, VS Code or agentsSandboxing and IsolationGuides and Discussion
Escaping Google Cloud Application Integration Sandbox: Straight into BorgSandboxing and IsolationGuides and Discussion
In sandboxes we shouldn't trust - limits of sandboxing AI agentsSandboxing and IsolationGuides and Discussion
Jennifer Marsman on sandboxing OpenClaw with Microsoft Execution ContainersSandboxing and IsolationGuides and Discussion
Philipp Schmid on sandbox network allowlists and egress-proxy credential injectionSandboxing and IsolationGuides and Discussion
Simon Willison on httpjail - HTTP sandboxing for coding agentsSandboxing and IsolationGuides and Discussion
VMs won't contain cyber-capable agentsSandboxing and IsolationGuides and Discussion
Your Container Is Not a Sandbox - The State of MicroVM Isolation in 2026Sandboxing and IsolationGuides and Discussion
Vulny says: prompt injection is just social engineering for computers.
📎
💰 get $POC --:--