the-agent-sandbox-taxonomy

the-agent-sandbox-taxonomy is a skill for Claude Code, Codex from kajogo777/the-agent-sandbox-taxonomy. It costs 0 tokens per session (12,281 once invoked), scanned B, original, no licence file.

A skill for evaluating and comparing the security of AI-agent sandboxes using the Agent Sandbox Taxonomy. A sandbox is a restricted environment that limits what an agent can access or change.

In plain words
What is it for?
It helps assess and compare how safely AI agents are isolated from files, systems, and other resources.
Why use it?
It provides a framework for discussing sandbox security in consistent terms instead of comparing environments informally.

Skill for Claude CodeCodex

Which agent this was written for is unclear — body not stored (licence); the path alone says nothing.

Good fit It helps assess and compare how safely AI agents are isolated from files, systems, and other resources.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/kajogo777/the-agent-sandbox-taxonomy/the-agent-sandbox-taxonomy
Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

Any agent
npx skills add kajogo777/the-agent-sandbox-taxonomy --skill the-agent-sandbox-taxonomy
Clone the repo
git clone --depth 1 https://github.com/kajogo777/the-agent-sandbox-taxonomy

Made for: Claude Code, Codex.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for the-agent-sandbox-taxonomy

README.md
[![agentmods](https://agentmods.dev/badge/skills/kajogo777/the-agent-sandbox-taxonomy/the-agent-sandbox-taxonomy/github.svg)](https://agentmods.dev/skills/kajogo777/the-agent-sandbox-taxonomy/the-agent-sandbox-taxonomy)
Your own site
<a href="https://agentmods.dev/skills/kajogo777/the-agent-sandbox-taxonomy/the-agent-sandbox-taxonomy"><img src="https://agentmods.dev/badge/skills/kajogo777/the-agent-sandbox-taxonomy/the-agent-sandbox-taxonomy/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for the-agent-sandbox-taxonomy

Your own site · 80×15
<a href="https://agentmods.dev/skills/kajogo777/the-agent-sandbox-taxonomy/the-agent-sandbox-taxonomy"><img src="https://agentmods.dev/badge/skills/kajogo777/the-agent-sandbox-taxonomy/the-agent-sandbox-taxonomy.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 0 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 12,281 The whole file, excluding the scripts and references it only reads on demand.
Security scan B 2 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin unknown No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5.1 $0.00000 $0.12281
Opus 5 $0.00000 $0.06141
Sonnet 5 $0.00000 $0.02456
Haiku 4.5 $0.00000 $0.01228

Measured 12d ago against content hash 0e572ad1ffa1, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade B, and why

the-agent-sandbox-taxonomy scanned grade B with 2 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 12d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Recursive force deletemediumDestructive command

rm -rf with a variable or a broad path is one typo away from removing the wrong tree.

| **T3** | Destructive Operations | Destroys or misconfigures resources, **both local and remote** | `rm -rf /`, cloud resource deletion via API, `kubectl delete namespace` |

Downgraded: this mod is about security review, or the phrase is quoted, so it is likely naming the pattern rather than instructing it.

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

curl -LO https://github.com/kajogo777/the-agent-sandbox-taxonomy/releases/latest/download/ast-probe-linux-amd64
SKILL.md · 718 lines

The source is not reproduced here

No licence file

A repository with no LICENSE is all rights reserved by default, so the body is not copied here. The metadata, the measurements and the link are.

Read it on GitHub

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 12d ago First seen · 718 lines · 0 tokens per session scan B 0e572ad1ffa1

Subscribe to this mod's changes

the-agent-sandbox-taxonomy is a skill published in the GitHub repository kajogo777/the-agent-sandbox-taxonomy (100 stars, last pushed 3mo ago), with no licence file. It costs nothing until one of its globs matches a file; then it loads 12,281 tokens. A static security scan graded it B with 2 findings (recursive force delete, makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

Related

Other skills, from other repositories