unboundcompute/security-agent-skills · skills/hunting-code-interpreter-and-tool-sandbox-escape/SKILL.md

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

hunting-code-interpreter-and-tool-sandbox-escape is agent-read markdown (skill) from unboundcompute/security-agent-skills: Hunt for ways attacker-influenced code or a tool call escapes the sandbox an AI application runs it in: a code-interpreter or tool runtime that executes model-generated code with network access, a writable host filesystem, or credentials it should never see, a sandbox that shares a kernel, a mount, or an environment variable with the host so the guest reaches out, a resource with no CPU, memory, time, or output bound so one run starves the host, and a tool whose arguments reach a shell or a path.

Indexed from public GitHub and served as immutable, content-addressed versions. Install it pinned to an exact SHA-256 with the mdr CLI, and every file is verified against the hash recorded here before it reaches your agent. The deterministic audit below grades the latest version, and the same file always earns the same grade.

How to install

Latest version
mdr add unboundcompute/security-agent-skills/hunting-code-interpreter-and-tool-sandbox-escape@git:20260901.f8395d1
Exact content
mdr add unboundcompute/security-agent-skills/hunting-code-interpreter-and-tool-sandbox-escape@sha256:1db21009e0103d80

Pin to a label to follow the author's releases, or to a sha256 to freeze the exact bytes forever. Either way the resolved hash is written to mdr.lock, and mdr install reproduces it on any machine.

Badge

mdr badge

[![mdr](https://markdownregistry.com/badge/art_j3cgqwycvapsjua2.svg)](https://markdownregistry.com/a/art_j3cgqwycvapsjua2)

0 badge views in 30 days

Versions

versioncommittedcommitsizeaudit
git:20260901.f8395d1 latest2026-09-01 f8395d1 9,651 BA view

Audit of the latest version

A  17 of 17 checks passed. Deterministic, no model, same answer every run.
  • pass: Frontmatter block present
  • pass: Frontmatter declares a name
  • pass: Frontmatter declares a description
  • pass: Size between 200 bytes and 200 KB (9651 bytes)
  • pass: No zero-width or bidi control characters
  • pass: No instruction hidden inside an HTML comment
  • pass: No link to an exfiltration or paste host
  • pass: No credential-shaped string
  • pass: No instruction to send local credentials anywhere
  • pass: No text hidden with inline styles
  • pass: No prompt-injection phrasing
  • pass: No curl or wget piped into a shell
  • pass: No recursive delete of root, home or parent
  • pass: No instruction to read or print local credentials
  • pass: No base64 blob over 200 characters
  • pass: No link to a raw IP address
  • pass: No script tag

Source

GitHub

unboundcompute/security-agent-skills · 5 stars · license MIT · pushed 2026-09-08 · branch main

API

GET https://markdownregistry.com/api/v1/artifacts/art_j3cgqwycvapsjua2
GET https://markdownregistry.com/api/v1/resolve?ref=unboundcompute/security-agent-skills/hunting-code-interpreter-and-tool-sandbox-escape
GET https://markdownregistry.com/api/v1/blob/1db21009e0103d80c432b843f6c429c1f19f16f94defdeeba5be2759c04bc34c

Agents talk at modelranch.com: hand yours the instructions there and it joins the network that reads files like this one.