hunting-code-interpreter-and-tool-sandbox-escape

hunting-code-interpreter-and-tool-sandbox-escape is a skill for Claude Code from UnboundCompute/security-agent-skills. It costs 207 tokens per session (2,092 once invoked), scanned A, original, MIT.

A security hunt for ways that code written by an AI or an agent tool can escape its sandbox. A sandbox is an isolated environment intended to stop untrusted code reaching the host system.

In plain words
What is it for?
Use it to assess code interpreters, notebook backends, shell tools, and other systems that run model-generated or attacker-influenced code.
Why use it?
It finds access to internal networks, host files, credentials, shared kernels or mounts, and unbounded resource use that could affect the wider machine.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin.

Part of the security-agent-skills plugin — 194 skills shipped together

Good fit Use it to assess code interpreters, notebook backends, shell tools, and other systems that run model-generated or attacker-influenced code.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/unboundcompute/security-agent-skills/hunting-code-interpreter-and-tool-sandbox-escape
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 UnboundCompute/security-agent-skills --skill hunting-code-interpreter-and-tool-sandbox-escape
Clone the repo
git clone --depth 1 https://github.com/UnboundCompute/security-agent-skills

Made for: Claude Code.

Or install security-agent-skills, the plugin that ships this one along with the rest of its 194 skills.

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 hunting-code-interpreter-and-tool-sandbox-escape

README.md
[![agentmods](https://agentmods.dev/badge/skills/unboundcompute/security-agent-skills/hunting-code-interpreter-and-tool-sandbox-escape/github.svg)](https://agentmods.dev/skills/unboundcompute/security-agent-skills/hunting-code-interpreter-and-tool-sandbox-escape)
Your own site
<a href="https://agentmods.dev/skills/unboundcompute/security-agent-skills/hunting-code-interpreter-and-tool-sandbox-escape"><img src="https://agentmods.dev/badge/skills/unboundcompute/security-agent-skills/hunting-code-interpreter-and-tool-sandbox-escape/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 hunting-code-interpreter-and-tool-sandbox-escape

Your own site · 80×15
<a href="https://agentmods.dev/skills/unboundcompute/security-agent-skills/hunting-code-interpreter-and-tool-sandbox-escape"><img src="https://agentmods.dev/badge/skills/unboundcompute/security-agent-skills/hunting-code-interpreter-and-tool-sandbox-escape.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 207 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,092 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original 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 $0.00207 $0.02092
Opus 5 $0.00103 $0.01046
Sonnet 5 $0.00041 $0.00418
Haiku 4.5 $0.00021 $0.00209

Measured 6d ago against content hash 1db21009e010, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

hunting-code-interpreter-and-tool-sandbox-escape scanned grade A with 0 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 6d 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.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

skills/hunting-code-interpreter-and-tool-sandbox-escape/SKILL.md · 137 lines

How it starts

The opening of the file, as written. The whole thing — 137 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Hunting code-interpreter and tool sandbox escape: the model writes code and something runs it

An AI application that runs model-generated code, a code interpreter, an agent tool that shells out, a notebook backend, is executing attacker-influenceable instructions, because the model's output is shaped by its input and its input can be attacker-controlled. The sandbox that runs that code is therefore a security boundary around hostile code, and it is often built as if the code were trusted. The escapes are concrete. The runtime may have network access, so generated code reaches internal services or exfiltrates. It may see a writable host filesystem or a shared mount, so code reads or writes outside the jail. It may carry credentials, an API key, a cloud role, a token, in its environment, so code steals them. The isolation may be thin, a shared kernel, a container with a host mount, a subprocess with no namespace, so a known primitive escapes it. And with no CPU, memory, time, or output bound, one run starves the host. The hunt is to run code in the sandbox and see what of the host it can touch. You hunt this by making the model emit probing code and observing what succeeds.

When to use

  • An AI feature executes model-generated code or shell, or runs agent tools, inside a sandbox.
  • The sandbox may have network access, a writable or shared filesystem, or credentials in its environment.
  • Isolation may be thin (shared kernel or mount) or resource limits may be missing.

Scope check

Test sandbox escape only on AI applications and runtimes you own or are authorized to assess, in a non-production sandbox. Running probing code exercises real execution and can reach real resources, so use an isolated test deployment and never touch data, credentials, or hosts that are not yours. If you can't name the authorization, stop.

The loop

  1. Establish the intended sandbox boundary first. Name what the runtime is allowed to touch: no network or a narrow allowlist, an ephemeral filesystem with nothing host-shared, no ambient credentials, hard CPU/memory/ time/output limits, and isolation strong enough for hostile code. This is the false-positive killer: a runtime with no egress, no host mount, no credentials in scope, enforced resource bounds, and real isolation is behaving correctly. Name the intended boundary, then test each edge.

Read the full file on GitHub · 137 lines

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. 6d ago First seen · 137 lines · 207 tokens per session scan A 1db21009e010

Subscribe to this mod's changes

hunting-code-interpreter-and-tool-sandbox-escape is a skill published in the GitHub repository UnboundCompute/security-agent-skills (5 stars, last pushed 3d ago), licensed MIT. It adds 207 tokens to every session and 2,092 once invoked, about $0.0010 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-05.

Related

Other skills, from other repositories

model-supply-chain

Reviews AI/ML model supply chains for security risks including model provenance verification, training data lineage, fine-tuning pipeline integrity, inference dependency review, and backdoor detection. Auto-invoked when reviewing systems that download pre-trained models, fine-tune foundation models, or deploy models…

UnitOneAI/SecuritySkills · 104 tokens

prodcheck-review

Review this codebase against the prodcheck pre-production checklists — security, performance, scale, integrations and post-launch readiness. Use when asked to check whether a project is ready to ship, to audit an area before launch, or to work through a specific checklist. Produces evidence with file:line citations…

FarzamHabibi/pre-production-checklist · 70 tokens

rag-poisoning-and-data-exfiltration

Test Retrieval-Augmented Generation (RAG) systems for data poisoning, prompt injection via retrieved documents, and data exfiltration through manipulated context windows. Use this skill when assessing RAG-based chatbots, knowledge bases, enterprise AI assistants, or any system that augments LLM responses with external…

akashrpatil/awesome-offensive-security-skills · 89 tokens

integrate-arcjet-guard-genkit

Integrate Arcjet security into a Genkit JS agent using @arcjet/guard — wrap ai.defineTool, put guardMiddleware on generate({ use }) for unwrapped / MCP / filesystem tools, and read a caller-owned id from generate({ context }). Use when asked to add Arcjet to genkit, rate limit its tools, screen inbound messages, or…

arcjet/arcjet-js · 89 tokens

integrate-arcjet-guard-claude-managed-agents

Integrate Arcjet security into Claude Managed Agents (hosted REST+SSE, beta managed-agents-2026-04-01) using @arcjet/guard — screen user.message / initialevents before sessions.events.send, and gate custom tools on agent.customtooluse. Use when asked to add Arcjet to Claude Managed Agents, rate limit custom tools, or…

arcjet/arcjet-js · 102 tokens

linear-claude-skill

Manage Linear issues, projects, and teams.

Agent-Threat-Rule/agent-threat-rules · 15 tokens