Flagged: privileged Docker. Scanned against the SlowMist agent-security taxonomy, refreshed every 8 hours. Full audit →
by 89luca89 · Agent Tool · ★ 98
Last updated: · Indexed by AgentSkillsHub · Auto-synced every 8h
🔒 Is clampdown safe to install? View the security audit →
Clampdown Run AI coding agents in hardened container sandboxes. AI coding agents run arbitrary code on your machine. clampdown confines them to a hardened container sandbox: filesystem access is restricted to your project, network egress is limited to the APIs the agent needs, and every tool container the agent spawns gets the same enforcement. Blue = sidecar. Yellow = agent. Green = tool containers. Red text = untrusted egress. Green text = trusted egress. Border color = namespace trust level (see legend in diagram). Container overview clampdown runs four container types with different privilege levels: Regist
| Stars | 98 |
| Forks | 9 |
| Language | Go |
| Category | Agent Tool |
| Quality Score | 64.6424452065971/100 |
| Open Issues | 10 |
| Last Updated | 2026-09-17 |
| Created | 2026-03-03 |
| Platforms | claude-code, docker, go |
| Est. Tokens | ~21k |
Looking for a clampdown alternative? If you're comparing clampdown with other agent tool tools, these 6 projects are the closest alternatives on Agent Skills Hub — ranked by topic overlap, star count, and community traction.
Unified CLI for running AI coding agents in isolated containers. Includes built-in local metrics collection, H
a fast, rootless container runtime and sandbox with no daemon. It runs workloads, including agent tool calls a
Your agent is a security risk, so treat it like one. yoloAI does AI agent sandboxing right.
Container-free, deny-by-default sandbox for AI coding agents. Kernel-enforced filesystem, network, and syscall
The missing linter and lsp for AI coding assistants. Validate CLAUDE.md, AGENTS.md, SKILL.md, hooks, MCP. Plug
A CLI tool for threat modeling and visualizing AI agents built using popular frameworks like LangGraph, AutoGe
Explore other popular agent tool tools:
clampdown is Run AI coding agents in hardened container sandboxes.. It is categorized as a Agent Tool with 98 GitHub stars.
clampdown is primarily written in Go. It covers topics such as agent, ai, ai-agents.
You can find installation instructions and usage details in the clampdown GitHub repository at github.com/89luca89/clampdown. The project has 98 stars and 9 forks, indicating an active community.
The top alternatives to clampdown on Agent Skills Hub include vibepod-cli, kern, yoloai. Each offers a different approach to the same problem space — compare them side-by-side by stars, quality score, and community activity.
Grades come from a rule-based scan built on the SlowMist agent-security taxonomy, covering 11 red-flag categories including credential harvesting, data exfiltration, and curl | sh installers. It is a first-layer scan, not a manual audit — we say so rather than overstate it.
The scale of the problem is documented independently: Liu et al. (2026), in a study of 31,132 agent skills, report that 26.1% contain security vulnerabilities. Our own full-catalog census is published as a citable open dataset.
Sources & who's responsible: