unboundcompute/security-agent-skills · skills/evaluating-model-guardrails/SKILL.md

evaluating-model-guardrails skillA

evaluating-model-guardrails is agent-read markdown (skill) from unboundcompute/security-agent-skills: Systematically test whether a model's safety and policy guardrails hold under adversarial pressure, as a repeatable evaluation rather than a one-off trick. Covers building a policy-grounded probe set, multi-turn escalation, encoding and obfuscation bypasses, role and context reframing, instruction-hierarchy conflicts, and measuring bypass rate with reproducible graded outcomes. Use when reviewing a model deployment, a system prompt, or a content-safety layer, or before shipping an assistant that.

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/evaluating-model-guardrails@git:20260816.a0bc1d1
Exact content
mdr add unboundcompute/security-agent-skills/evaluating-model-guardrails@sha256:3900aa4187fb53f7

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_qt2xjhwjdxnx46uv.svg)](https://markdownregistry.com/a/art_qt2xjhwjdxnx46uv)

0 badge views in 30 days

Versions

versioncommittedcommitsizeaudit
git:20260816.a0bc1d1 latest2026-08-16 a0bc1d1 6,881 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 (6881 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_qt2xjhwjdxnx46uv
GET https://markdownregistry.com/api/v1/resolve?ref=unboundcompute/security-agent-skills/evaluating-model-guardrails
GET https://markdownregistry.com/api/v1/blob/3900aa4187fb53f7d545715ac3bb69690fcf5b8e8825753242d88831cbfd23d6

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