Results for “sandbox”

Provides isolated, agent-native sandboxes for code execution, live preview URLs, browser automation, and access to 50+ tools via CLI or HTTP, with no SDK or API keys required.

Prevents AI-introduced regressions with sandbox-mode API testing, automated bug-check workflows, and patterns that catch blind spots where the same model writes and reviews code.

AIDefence security layer with prompt injection blocking, input validation, sandboxed execution, output sanitization, and STRIDE threat modeling.

Clawdex — dual-engine coding agent. Claude Code (reasoning + planning) + OpenAI Codex (fast execution) + Browser Use boxes (web research) + Upstash compute boxes (isolated sandboxes).

Scaffolds a program.md research program for autoresearch by auto-detecting codebase signals and interviewing for missing details.

Analyzes prompt injection, retrieval poisoning, memory contamination, planner drift, and tool-boundary abuse in agentic systems, mapping trust boundaries and proving exploit chains.

Build durable backend AI agents with the eve framework. Use when creating, editing, or debugging an eve project — agent instructions, skills, tools, connections, channels, sandboxes, subagents, schedules, or evals.

Runs a plan file through the Codex CLI as an independent adversarial reviewer, then folds accepted findings back into the plan. Read-only sandbox; Codex never edits.

Runs the current git diff through the Codex CLI for an independent, read-only second-opinion review, then triages findings back into the session for Claude to apply fixes.

Use this skill when designing, reviewing, migrating, or debugging MCP Apps / SEP-1865 interactive UI resources for MCP servers, including dashboards, forms, visualizations, tool-driven workflows, OpenAI Apps SDK migration, MCP-UI compatibility, sandboxing, host support, security review, provenance, and fallback UX.

Use for designing, creating, reviewing, or debugging Model Context Protocol server configuration for GitHub Copilot in Visual Studio Code, including .vscode/mcp.json, transports, inputs, trust, sandboxing, and tool scope. Do not use for implementing an MCP server, ordinary HTTP clients, or silently installing or starting external software.

Sets up a codebase for reliable agent-driven development by making it legible (structured docs, custom lints, code graph), executable (one-command dev stack, cloud sandbox), and verifiable (e2e gate, verify-before-ship loop).

Provides Codex CLI delegation workflows for complex code generation and development tasks using OpenAI's GPT-5.3-codex models, including English prompt formulation, execution flags, sandbox modes, and safe result handling. Use when the user explicitly asks to use Codex for complex programming tasks such as code generation, refactoring, or architectural analysis. Triggers on "use codex", "delegate to codex", "run codex cli", "ask codex", "codex exec", "codex review".

Drive Airship (`@airshiplabs/cli`), a CLI that puts a visual, pannable design canvas in front of a running dev server so an engineer can click an element, describe a change, and have Claude Code, Codex, or OpenCode edit the underlying source file directly — no plugin, no build config, nothing added to the project. Use when the user wants to launch a visual editor over a local dev server (`npx @airshiplabs/cli --target <port>`), pick or compare coding agents (`--agent claude|codex|opencode`) for live UI edits, sandbox agent edits with `--safe`, scaffold an `airship.config.json` (`airship init`), or diagnose a broken setup (`airship doctor`). Triggers on: "airship", "@airshiplabs/cli", "visual editor for my codebase", "click to edit UI", "design canvas over dev server", "airship doctor", "airship init", "pair Claude Code with a visual editor on localhost".