sandboxing-agentic-systems

sandboxing-agentic-systems is a skill for Claude Code, Codex from Hoja-Solutions/agent-stdlib. It costs 173 tokens per session (845 once invoked), scanned A, original, MIT.

A guide for containing coding agents that run programs or process untrusted text and web content.

In plain words
What is it for?
Use it to plan filesystem and network isolation, protect credentials, and treat fetched pages and tool results as possible prompt-injection sources. Prompt injection is text that tries to steer an agent away from its assigned task.
Why use it?
It reduces the risk that an agent or a command it starts will access unauthorised files, send data over the network, or follow malicious instructions hidden in tool output.

Skill for Claude CodeCodex

Part of the agent-stdlib plugin — 14 skills, 2 commands, 1 agent, 2 hooks, 2 MCP servers shipped together

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.

agentmods
npx agentmods add skills/hoja-solutions/agent-stdlib/sandboxing-agentic-systems
Any agent
npx skills add Hoja-Solutions/agent-stdlib --skill sandboxing-agentic-systems
Clone the repo
git clone --depth 1 https://github.com/Hoja-Solutions/agent-stdlib

Made for: Claude Code, Codex.

Or install agent-stdlib, the plugin that ships this one along with the rest of its 14 skills, 2 commands, 1 agent, 2 hooks, 2 MCP servers.

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 sandboxing-agentic-systems

README.md
[![agentmods](https://agentmods.dev/badge/skills/hoja-solutions/agent-stdlib/sandboxing-agentic-systems.svg)](https://agentmods.dev/skills/hoja-solutions/agent-stdlib/sandboxing-agentic-systems)
Your own site
<a href="https://agentmods.dev/skills/hoja-solutions/agent-stdlib/sandboxing-agentic-systems"><img src="https://agentmods.dev/badge/skills/hoja-solutions/agent-stdlib/sandboxing-agentic-systems.svg" alt="Measured on agentmods" height="20"></a>
Per session 173 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 845 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00173 $0.00845
Opus 5 $0.00086 $0.00423
Sonnet 5 $0.00035 $0.00169
Haiku 4.5 $0.00017 $0.00085

Measured 5d ago against content hash d9fc2fcdc9e7, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

sandboxing-agentic-systems 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 5d 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/sandboxing-agentic-systems/SKILL.md · 54 lines

How it starts

The opening of the file, as written. The whole thing — 54 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Sandboxing agentic systems

Source: How we contain Claude and Beyond permission prompts. Single-layer skills exist (a Seatbelt-profile generator, Docker configs). None package the end-to-end, threat-model-driven layering, which is where containment actually comes from.

Contain at the environment layer first, steer at the model layer second. A prompt or a classifier is probabilistic and will miss an edge case eventually. A filesystem mount and a firewall rule are deterministic: they hold on the case you did not think of. Build the deterministic boundary first and treat model-layer guidance as a second line, never the only one.

Isolate the filesystem

Scope reads and writes to the working directories the task needs. Block parent and system paths. Two details decide whether it holds:

  • Use an OS primitive that also covers spawned subprocesses. Linux bubblewrap and macOS Seatbelt confine the process tree, so a shell command the agent runs is confined too. An application-level path check does not survive the agent shelling out.
  • Validate paths before symlink resolution. A symlink inside an allowed directory can point at /etc. Resolve and check the real target, not the link.

Offer mount modes that match the task: read-only, read-write, and read-write-without-delete for work that should add but never remove.

Isolate the network

Route every outbound connection through an egress proxy with allow and deny lists, and prompt on a new destination. The non-obvious part:

Check provenance, not just the destination domain. Allowlisting a domain opens every endpoint reachable through it, including ones that exfiltrate. Validate where the request came from and what it carries, not only where it is going.

Treat incoming content as hostile

Anything a network-enabled tool returns is a possible prompt-injection payload, including a fetched web page, an API response, or a file from a shared drive. Run tool results through a lightweight classifier before they enter the model's context. Defer parsing or executing project-local config, localhost listeners, and similar local-but-untrusted inputs until the user has explicitly consented.

Read the full file on GitHub · 54 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. 5d ago First seen · 54 lines · 173 tokens per session scan A d9fc2fcdc9e7

Subscribe to this mod's changes

sandboxing-agentic-systems is a skill published in the GitHub repository Hoja-Solutions/agent-stdlib (1 stars, last pushed 1mo ago), licensed MIT. It adds 173 tokens to every session and 845 once invoked, about $0.0009 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 2026-08-31.