unboundcompute/security-agent-skills · skills/testing-llm-insecure-output-handling/SKILL.md

testing-llm-insecure-output-handling skillA

testing-llm-insecure-output-handling is agent-read markdown (skill) from unboundcompute/security-agent-skills: Test what happens after the model speaks: whether an application trusts model output and passes it, unescaped, into a browser, a terminal, a shell, a database, or another system. Covers model-driven XSS and markup injection, data exfiltration through rendered markdown images and links, terminal and ANSI escape injection, invisible-unicode and ascii smuggling in output, and output used to build code, SQL, or shell commands. Use when reviewing any app that renders, executes, or forwards LLM output.

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/testing-llm-insecure-output-handling@git:20260816.a6124f2
Exact content
mdr add unboundcompute/security-agent-skills/testing-llm-insecure-output-handling@sha256:2589c2b79e9db66c

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_bew75w2rriqfviw6.svg)](https://markdownregistry.com/a/art_bew75w2rriqfviw6)

0 badge views in 30 days

Versions

versioncommittedcommitsizeaudit
git:20260816.a6124f2 latest2026-08-16 a6124f2 6,801 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 (6801 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_bew75w2rriqfviw6
GET https://markdownregistry.com/api/v1/resolve?ref=unboundcompute/security-agent-skills/testing-llm-insecure-output-handling
GET https://markdownregistry.com/api/v1/blob/2589c2b79e9db66c7c21d260217d0160f4403d23a9e9d7bfd30960c154754580

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