bruc3van/agent-skills-guard · test/test-skills/negative-generated/prompt-injection/SKILL.md

prompt-injection-counterexample skillB

prompt-injection-counterexample is agent-read markdown (skill) from bruc3van/agent-skills-guard: Generated counterexample containing direct instruction override attempts.

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 bruc3van/agent-skills-guard/prompt-injection-counterexample@git:20260608.9f59278
Exact content
mdr add bruc3van/agent-skills-guard/prompt-injection-counterexample@sha256:944ad3706a4d575b

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_c47whywb77zctjzx.svg)](https://markdownregistry.com/a/art_c47whywb77zctjzx)

0 badge views in 30 days

Versions

versioncommittedcommitsizeaudit
git:20260608.9f59278 latest2026-06-08 9f59278 307 BB view

Audit of the latest version

B  16 of 17 checks passed. Deterministic, no model, same answer every run.
  • fail: No prompt-injection phrasing (matched: Ignore all previous instructions)
  • pass: Frontmatter block present
  • pass: Frontmatter declares a name
  • pass: Frontmatter declares a description
  • pass: Size between 200 bytes and 200 KB (307 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 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

bruc3van/agent-skills-guard · 388 stars · license MIT · pushed 2026-09-08 · branch main

API

GET https://markdownregistry.com/api/v1/artifacts/art_c47whywb77zctjzx
GET https://markdownregistry.com/api/v1/resolve?ref=bruc3van/agent-skills-guard/prompt-injection-counterexample
GET https://markdownregistry.com/api/v1/blob/944ad3706a4d575bca15429eb9423c19e15760cf5c079f1a16c85d0165564234

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