borghei/claude-skills · engineering/skill-security-auditor/SKILL.md

skill-security-auditor skillA

skill-security-auditor is agent-read markdown (skill) from borghei/claude-skills: Security audit and vulnerability scanning for AI agent skills before install. Detects prompt injection, dangerous code, exfiltration, credential harvesting, and supply chain risks. Use when evaluating untrusted skills or gating installs..

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 borghei/claude-skills/skill-security-auditor@v1.1.0
Exact content
mdr add borghei/claude-skills/skill-security-auditor@sha256:cdac08ee3995c306

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_xjtx4a5mrl3a3vmo.svg)](https://markdownregistry.com/a/art_xjtx4a5mrl3a3vmo)

0 badge views in 30 days

Versions

versioncommittedcommitsizeaudit
v1.1.0 latest2026-06-22 65b93aa 6,800 BA view · diff
v1.1.02026-06-17 8980a67 6,192 BA view · diff
v1.0.02026-06-17 0c19211 20,450 BB view · diff
v1.0.02026-03-30 6b5a5d8 20,681 BB view · diff
v1.0.02026-03-21 36e3f67 20,648 BB 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 (6800 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

borghei/claude-skills · 778 stars · license NOASSERTION · pushed 2026-08-12 · branch main

API

GET https://markdownregistry.com/api/v1/artifacts/art_xjtx4a5mrl3a3vmo
GET https://markdownregistry.com/api/v1/resolve?ref=borghei/claude-skills/skill-security-auditor
GET https://markdownregistry.com/api/v1/blob/cdac08ee3995c306b817fa7b1cd98d78760d0e2af0d0637bc06c5eb8f6552afd

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