57 results for “Box”

MOSS-Image is an open-source text-to-image model family from OpenMOSS with a 5B backbone, released October 2026 as MOSS-Image-Base and MOSS-Image-SFT. It supports JSON layout control with bounding boxes, text rendering inside images, and prompts up to 4K tokens. The repo gives a Diffusers pipeline, a Gradio app, a ComfyUI plugin, LoRA training guidance, a prompt-enhancer skill and day-0 SGLang and vLLM-Omni support.

github.comrepoAdded 20 Oct 2026, published 16 Oct 2026🧠 AI

bitra (CLI name tra) is an MIT-licensed Python framework from Bijective Labs for autonomous trading agents. Language models only read system-computed figures and give opinions, while deterministic code prices the round trip, applies declared limits, sizes the trade and sends one order with stop attached. Every cycle's briefs, answers and refusals are stored on disk with hashes. It supports many model providers and ccxt venues, with sandbox, demo and mainnet tiers.

github.comrepoAdded 25 Oct 2026, published 13 Oct 2026🧠 AI

bigarrow is an MIT-licensed, single-binary Swift macOS CLI that draws a click-through arrow and sign over all windows so an AI agent can show a human where to click, paste or act (permission prompts, 2FA, OAuth consent). It ships an Agent Skills package (installed via `bigarrow install-skill`) for Claude Code and Codex, with JSON output and exit codes, and can target by Accessibility label, coordinates, window or Peekaboo snapshot. The README documents the skill's token cost (182 tokens for the description, 1,398 for the instructions) and 104 automated tests.

github.comrepoPublished and added 9 Oct 2026🧠 AI

MXC is Microsoft's cross-platform sandboxed code execution system for running untrusted workloads — model output, plugins, and tool calls — behind a unified containment model with Rust, .NET, and Node SDKs. It offers multiple containment backends (ProcessContainer, Windows Sandbox, LXC, Bubblewrap, Seatbelt, MicroVM/Nanvix, Hyperlight, WSLC) with JSON-based filesystem, network, and UI policies, plus diagnostics like audit mode for building policies from observed access.

github.comrepoAdded 8 Oct 2026🧠 AI

MXC is Microsoft's cross-platform sandboxed code execution system for running untrusted code such as LLM/agent output, plugins, and tools, offering containment backends ranging from OS-native process sandboxes (Windows Sandbox, LXC, Bubblewrap, Seatbelt) to full VMs (Nanvix MicroVM, Hyperlight). It exposes a unified JSON-based policy model for filesystem, network, and UI access controls, with Rust, .NET, and Node SDKs plus diagnostic tooling (audit mode, access-denied logging) to help developers tune containment rules for agentic workloads.

github.comrepoAdded 8 Oct 2026🛡️ Security

nanoMuse is an open-source personal AI agent that runs across phone, desktop, and web, built on an on-device sandbox (OpenMinis with proot/Alpine Linux on mobile) and the DeepSeek Harness on desktop with a Python runtime for tool use. Devices share one account and sync conversations through a relay (self-hostable), while the agent proactively acts, retains memory, and pauses before irreversible actions; it is released GPL-3.0-or-later with documentation on install, self-hosting, connectors, and memory.

github.comrepoPublished and added 7 Oct 2026🧠 AI

Release notes for python-1.20.0 of Microsoft's Agent Framework, an open-source agent/workflow orchestration library. This release adds native vector-store connectors for DuckDB, SQL Server and MongoDB plus a TypeSafe AI connector, redesigns Foundry hosting around request-scoped agent factories and sandbox-isolated sessions, adds computer-use support to Responses clients, and ships Magentic manager and handoff-routing improvements for multi-agent orchestrations alongside a large batch of MCP, Bedrock, Gemini, Anthropic and Ollama provider fixes.

github.comrepoAdded 6 Oct 2026🧠 AI

OpenShell is NVIDIA's open-source runtime for safely running fleets of autonomous AI agents: each agent runs in an isolated sandbox where kernel-level controls enforce a declared policy over file access, syscalls, and network connections, and credentials are injected only for approved endpoints rather than exposed to the agent directly. Policy changes are checked with formal verification to flag risky new access (new hosts, new API methods) before they're approved, and the project ships a CLI, gateway, Kubernetes/Helm deployment, and a tutorial running OpenCode against an OpenRouter model.

github.comrepoAdded 1 Oct 2026🛡️ Security

OpenShell is NVIDIA's open-source runtime for running fleets of autonomous AI agents inside isolated sandboxes. Declarative policies cover filesystem, syscall, process and network access. These are enforced at the kernel level, and credentials are injected only into requests bound for approved endpoints. Policy changes are checked with formal verification so risky new access waits for human review. It ships a CLI, a gateway control plane (Helm deployment on Kubernetes), SDKs, extensibility hooks (middleware, interceptors, compute drivers) and installable agent skills, and it can run agents such as OpenCode.

github.comrepoAdded 1 Oct 2026🧠 AI

CAIRN is a Cisco Talos research toolkit that identifies and attributes AI-integrated malware purely from VirusTotal metadata — no binary downloads or detonation — by running a tiered YARA ontology (T1/T2/T3) over composed scan text (AV strings, PE resources, Sigma/sandbox behavioral data, embedded URLs) and layering on sentence-transformer embeddings with HDBSCAN clustering for semantic family attribution. It has produced confirmed family reports for AI-malware such as PROMPTLOCK, LAMEHUG, PROMPTSTEAL, QUIETVAULT, CLOSEDQUORUM, and FRUITSHELL, each cross-verified by hands-on Talos reverse engineering before publication.

github.comrepoAdded 30 Sep 2026🛡️ Security

OpenShell is NVIDIA's open-source runtime for running fleets of autonomous AI agents with restricted, policy-governed access to files, system calls, network, and credentials. It enforces policy at the kernel level inside isolated sandboxes (per-agent, with Docker/Podman/virtualization backends) and uses formal verification to flag risky policy changes — such as an agent gaining a new host or API access with credentials — before they take effect, so changes can wait for human review. It ships a CLI, a gateway control plane, Kubernetes/Helm deployment, and installable agent skills for writing and debugging sandbox policies.

github.comrepoAdded 29 Sep 2026🧠 AI

OpenShell is NVIDIA's open-source runtime for running fleets of autonomous AI agents in isolated sandboxes, enforcing per-agent policies on filesystem, syscall, and network access at the kernel level and injecting credentials only for approved endpoints. Policy changes go through a formal-verification step (an 'advisor'/'prover') that flags newly granted risky access, such as a new host reachable with credentials, before it's applied, and it deploys via Docker/Podman/host virtualization or Kubernetes with Helm.

github.comrepoAdded 29 Sep 2026🛡️ Security

AX is Google's declarative orchestrator for running large numbers of autonomous agent workloads on Kubernetes, built on top of "Agent Substrate" for sandboxed execution. Agents are declared via YAML manifests (Task, Workspace, Model) similar to kubectl, and applied with an `ax` CLI that supports apply/get/watch/ssh/suspend/resume, treating agent runs as a distinct workload type distinct from stateless services or batch jobs.

github.comrepoAdded 26 Sep 2026🧠 AI

A GitHub PoC chaining two n8n CVEs into unauthenticated RCE: CVE-2026-21858 abuses a Content-Type confusion in the Form Trigger/Respond-to-Webhook nodes to read arbitrary files (e.g. /proc/self/environ, the SQLite database, and the config file), from which the attacker derives the JWT secret from n8n's encryptionKey and forges an admin session cookie. That admin access is then used to create a workflow exploiting CVE-2025-68613, an expression-injection sandbox bypass (`this.process.mainModule.require`) that yields command execution, all demonstrated with a working Python exploit script and Docker lab against n8n 1.65.0. It notes the exploit was developed independently of a prior Cyera/Dor Attias write-up on a related n8n chain and details the specific vulnerable workflow pattern (file-upload form + binary Respond node) required for exploitation.

github.comrepoAdded 26 Sep 2026🛡️ Security

VulnHunter is a maintained fork of Capital One's open-source agentic security scanner, reworked to run on any agent harness (Claude Code, Codex, Grok/OpenCode) instead of being Claude-Code-specific. The fork's distinguishing work is engineering, not security findings: portable "skill" prompt files with an explicit environment contract, an installer that fails loudly instead of guessing paths, Docker-based sandboxed exploit validation, and a benchmark harness that ran six full scans of one production Go service across five model/harness stacks, finding that result counts swung from 3 to 42 findings depending on how rigorously exploits were validated. It ships three composable skills (/vulnhunt, /vulnhunter-fix, /vulnhunt-fix-verify), a headless batch-runner (harness/), and a deterministic manifest-writing CLI (vh).

github.comrepoAdded 6 Oct 2026, published 22 Sep 2026🧠 AI

Simreal-MLBench is the open, minimal slice of ML Benchmark, a verifiable evaluation environment for machine learning research agents, covering 60 tasks across tabular learning, forecasting, vision, language, audio, multimodal and structured scientific data. It splits an open, Apache-2.0 layer (task definitions, scoring rule, verification tooling) from a commercial operated layer (SimReal's sandboxed runtime, gateway, submission broker and official scoring), scores tasks as 100xp^2 against a frozen reference leaderboard, enforces a source-blind two-submission protocol, and provides full provenance for every published number. It is positioned as an alternative to MLE-bench with a distinct task selection, resource protocol, and scoring scheme, aimed at supporting RLVR and agent self-improvement research.

github.comrepoAdded 26 Sep 2026, published 21 Sep 2026🧠 AI

Cua is an open-source platform for computer-use agents: isolated cloud desktops (Fleets), a Sandbox SDK, local macOS/Linux VM management (Lume), a Cua Driver for controlling native apps/browsers via CLI/MCP/SDKs, and Cua-Bench for building and evaluating computer-use tasks. It also introduces CUA-S1, a family of small specialized "System 1" models that make fast, bounded decisions (e.g., scoring form field values from structured UI/document data) rather than generating agent actions token-by-token, with the first CUA-S1-FORMS model and dataset released on Hugging Face. The project is MIT-licensed with some optional components (cua-som, cua-perception's OmniParser integration) carrying AGPL-3.0 obligations.

github.comrepoAdded 26 Sep 2026, published 19 Sep 2026🧠 AI

Shor is a source-available, multi-tenant autonomous pentesting platform where a ~17-agent LLM pipeline (discovery, hypothesis, adversarial screening jury, exploitation, proof replay) attacks a target URL and optionally its connected source repo. It wields 30+ real offensive tools (sqlmap, dalfox, nuclei, jwt_tool, hydra, ffuf, etc.) plus SAST/secret/SCA tools (Semgrep, Gitleaks, TruffleHog, OSV-Scanner, Trivy) in white-box mode, and only reports findings whose PoC is deterministically re-executed and confirmed by a code-enforced safety layer under a signed Rules of Engagement, with scan authorization gated behind single-use human-minted tokens on its MCP/automation surface.

github.comrepoAdded 22 Sep 2026, published 19 Sep 2026🛡️ Security

A GitHub-hosted, CC0-licensed index of 281 public writeups on attacks against AI agents, organized into six categories: indirect prompt injection, direct prompt injection/jailbreaks/guardrail bypass, MCP and agent tooling, AI platform/infrastructure bugs, classic web bugs in AI product surfaces, and AI used as an attacker's tool. Entries span 2021-2026 and include major disclosures like GeminiJack, ForcedLeak, Clinejection, CVE-2025-53773 (GitHub Copilot RCE), and dozens of Johann Rehberger/PromptArmor/qual1a writeups covering exfiltration, MCP OAuth flaws, and coding-agent sandbox escapes. Comes with an accompanying blog post "How to Hack AI Agents" and a scripted links.txt for automation.

github.comrepoAdded 22 Sep 2026, published 17 Sep 2026🛡️ Security

security-audit-skill is a Cloudflare open-source coding-agent skill that turns an AI coding agent into a structured vulnerability hunter, running six phases: reconnaissance into architecture.md/coverage-ledger.json, coverage-led hunting by isolated sub-agent "hunters," adversarial candidate validation, structured findings.json output validated against a report-schema.json, independent re-verification of claims, and target-neutral report generation (REPORT.md, FINDINGS-DETAIL.md, NEEDS-VALIDATION.md). It is installed via the Skills CLI (`npx skills add`), uses Node.js validators (validate-coverage-ledger.cjs, validate-findings.cjs), requires a sandboxed environment for safely executing target code/tests/fuzzers, and is the single-repo seed for Cloudflare's larger fleet-wide vulnerability discovery harness described in a companion blog post.

github.comrepoAdded 22 Sep 2026, published 15 Sep 2026🛡️ Security

RepoGuardBench is a benchmark and accompanying paper that measures whether local open-weight coding agents (Qwen2.5-Coder 1.5B-14B via Ollama) stay on the bug-fix task when repository artifacts — README files, issue text, code comments, test logs, and agent-rule files — carry inert prompt-injection instructions. It evaluates five lightweight context- and action-level defenses (D0-D5, including a path-only action gate) across seven metrics in a sandboxed task workspace, finding no statistically clear utility winner among them. The project ships a deterministic no-GPU smoke test, paper-claim verification scripts, and reproducible tables/figures under MIT (code) and CC BY 4.0 (data) licenses.

github.comrepoAdded 22 Sep 2026, published 13 Sep 2026🛡️ Security

Exploitarium is a consolidated GitHub archive of an independent researcher's proof-of-concept vulnerability writeups, merging over a dozen former standalone PoC repos into one. It covers diverse real-world targets including RustDesk session permission bugs, an OpenSSH agent lock provider bypass, a Redis VSET duplicate HNSW ID RCE, a QEMU CXL Type3 mailbox escape, Firefox native/backup NSS RCE PoCs, libssh2 CVE-2026-55200, Nextcloud federated share bearer token issues, and more. The author documents an AI-assisted fuzzing workflow (hand-typed PoCs, AI-drafted READMEs) and credits prior work on an objdump OOB write finding.

github.comrepoPublished and added 7 Sep 2026🛡️ Security

Pooled runs one open model (Qwen 3.6 35B MoE, a 27B dense hybrid, smaller Qwen3/SmolLM) across devices in a browser "room". Each tab holds a slice of layers and runs them on its own GPU with custom WGSL kernels. Hidden states pass over WebRTC, and speculative decoding is checked against plain decoding by golden tests. It also ships a Code-mode agent loop with a sandboxed preview, and an npx CLI bridge (@pooled/cli) that exposes the room as an OpenAI Chat Completions/Responses and Anthropic Messages endpoint with grammar-constrained tool calling, so Codex CLI, Claude Code and opencode can use it. The README includes latency-injected benchmarks, a comparison with exo, Petals, llama.cpp RPC and WebLLM, and a threat model.

github.comrepoAdded 16 Oct 2026, published 1 Sep 2026🧠 AI

AHA (Agent Hacks Agent) is an autonomous red-teaming framework where a researcher agent iteratively hypothesizes attacks, runs them against Docker-sandboxed victim agents (built on Claude Code and Codex, targeting frontier models like Minimax-M2.7, Kimi-K2.6, and Deepseek-V4-Pro), and accumulates a persistent Vulnerability Concept Graph of reusable attack mechanisms rather than one-off jailbreak strings. It reports held-out Attack Success Rate evaluations showing these mechanisms — notably a "claimed-authorization" bypass pattern — transfer across scenarios and victim models (up to ~88% of native ASR), and ships as registry-discovered plugins for scenarios like AgentHazard, AgentDojo-style indirect injection, and DecodingTrust-Agent.

github.comrepoPublished and added 25 Aug 2026🛡️ Security

Cloudflare Computer is a preview virtual filesystem living inside a Durable Object, with authoritative state in SQLite exposed through three pluggable execution backends: a full Linux container mounted via FUSE and capnweb RPC, an isolated shell (just-bash) running in a Dynamic Worker, and isolated JavaScript modules in a fresh Dynamic Worker with scoped fs/git/artifacts access. It's designed as sandboxing infrastructure for AI agents, with examples demonstrating per-backend egress policy controls (none/all/custom) and MCP-based code execution tools, making it relevant to securely isolating and constraining agent/LLM code execution.

github.comrepoAdded 3 Sep 2026, published 25 Aug 2026🛡️ Security

Cumora is a cross-platform team-chat application where AI agents sit alongside humans as first-class participants — holding persistent personas and memory, claiming Kanban work, coordinating with each other, and sending real email — rather than only responding when addressed. Agents can run on Cumora's cloud (per-agent Kubernetes pods driving a multi-hop tool-calling loop over the OpenAI Responses API) or in "Bring Your Own Agent" mode, pairing a local Mac/VPS daemon with an existing coding-agent backend (Claude Code, Codex, Cursor Agent, Gemini CLI, OpenCode, Qwen Code, Google Antigravity, etc.) while keeping provider keys off the server. The repo documents a concrete coordination design — a seen-cursor freshness gate that holds stale replies, atomic claims on units of work, a small-brain triage gate, and a transactional Postgres outbox for realtime fan-out — making it a useful reference for building multi-agent systems that avoid agents colliding on shared work.

github.comrepoAdded 30 Sep 2026, published 17 Aug 2026🧠 AI

Prime Agent is an open source coding and research agent built on a persistent Python REPL and subagent architecture. Its documentation explicitly warns that it executes model generated code with full user permissions and is not a security sandbox, advising users to only run trusted repositories, instructions, and skills.

github.comrepoPublished and added 9 Aug 2026🛡️ Security

DarkMoon is a self-hosted, GPLv3 AI penetration testing platform that orchestrates 50 specialist agents over an MCP-gated toolbox (Nuclei, BloodHound, sqlmap, Impacket, Naabu, httpx, ffuf, etc.) to autonomously run recon-to-exploitation across web, API, Active Directory, Kubernetes, multi-cloud, CI/CD, databases, IoT firmware, and AI/LLM inference endpoints. It uses a Privacy Gateway that tokenizes real IPs/hosts/credentials into placeholders so raw infrastructure data never reaches the (optionally local, e.g. Ollama/llama.cpp) LLM, and can generate sandbox-validated, exploit-retested pull requests for findings. It also ships a dedicated LLM agent that probes OpenAI-compatible/Ollama/vLLM/TGI inference endpoints for the OWASP LLM Top 10 (prompt injection, jailbreaks, system-prompt leakage) using garak-backed probes.

github.comrepoPublished and added 5 Aug 2026🛡️ Security

OpenHack is an open-source, agentic vulnerability scanner CLI that runs a recon -> hunter -> validation -> verification pipeline over a codebase using open-source LLMs. It uses category- and feature-based hunter agents to find candidate vulnerabilities, validator agents to confirm them, and optional Docker-based sandbox plus headless-browser verification to actually exploit findings (e.g. XSS, SQLi, command exec) and confirm them with real HTTP/DOM execution, reporting CVSS-scored findings with fixes.

github.comrepoPublished and added 2 Aug 2026🛡️ Security

QM is an MIT-licensed, self-hosted "multiplayer" agent harness that lets a company deploy a shared coding/ops agent across Slack and a web app, with per-person and per-room isolated sandboxes, memory, keychains, permissions, and crons. Its security model centers on an org-wide posture (Strict pauses every tool call for approval; Auto blocks private-network access and applies optional content screening; Dangerous disables both) layered under a predeclared command policy that hard-denies things like recursive deletes, plus an explicit Isolated/Open sharing posture that governs cross-scope memory and file access with provenance labeling and audit trails. It supports pluggable harnesses (Pi, OpenCode, Codex, Claude Code) behind a common core and documents its threat model and operator assumptions in SECURITY.md.

github.comrepoAdded 3 Sep 2026, published 1 Aug 2026🛡️ Security