AGENTS.mdA
AGENTS.md from netresearch/security-audit-skill is an AGENTS.md file: the standing instructions coding agents read in that repo.
mdr add netresearch/security-audit-skill/AGENTS.md@git:20261001.d3006ffPins git:20261001.d3006ff in mdr.lock. Pin the fingerprint instead.
- Audit grade
- A, 14 of 14 checks passed
- Kind
- AGENTS.md file
- Repository
- netresearch/security-audit-skill
- Path
AGENTS.md- Versions recorded
- 4
- Latest version
- git:20261001.d3006ff, committed Oct 1, 2026
- First version recorded
- Mar 22, 2026
- Size
- 2,894 bytes
- Repository stars
- 52
- License
- a license file GitHub does not identify
Collected from public GitHub. Every version is saved exactly as it was and never changes. Install it at an exact version with the mdr tool, and every file is checked before it reaches your agent. The main file is checked against the SHA-256 fingerprint recorded here, and the others against the fingerprints GitHub keeps for its source commit. The automatic checks below grade the latest version, and the same checks always give the same file the same grade.
What the file says
<!-- SPDX-License-Identifier: CC-BY-SA-4.0 --> <!-- SPDX-FileCopyrightText: Netresearch DTT GmbH --> # Security Audit Skill Security audit patterns (OWASP Top 10, CWE Top 25, CVSS v4.0) and deep PHP/TYPO3 code scanning with 80+ checkpoints. ## Repo Structure ``` security-audit-skill/ ├── skills/security-audit/ # Skill definition, checkpoints, scripts, references │ ├── SKILL.md # Skill metadata and trigger patterns │ ├── checkpoints.yaml # 80+ automated security checkpoints │ ├── scripts/ # Audit scripts (security-audit.sh, github-security-audit.sh) │ ├── references/ # 41 reference guides (OWASP, CWE, CVSS, etc.) │ └── evals/ # Skill evaluation tests ├── hooks/ # PreToolUse hook configuration (hooks.json) ├── scripts/ # Utility scripts (check_risky_command.py) ├── Build/ # Build utilities ├── .github/workflows/ # CI (ci.yml, lint.yml, release.yml, auto-merge-deps.yml) ├── composer.json # PHP package definition ├── SECURITY.md # Security policy …
Read the whole file at its exact version.
How to install
mdr add netresearch/security-audit-skill/AGENTS.md@sha256:5bc3165b28dd66fdThe line at the top of this page pins the label git:20261001.d3006ff, which is what most people want. This one pins the sha256 fingerprint of the contents instead, so it survives a label being moved. Either way the exact version is written to mdr.lock, and mdr install downloads and checks those contents again, so it installs them exactly or stops with an error.
[](https://markdownregistry.com/a/art_62exgalv5rfj3qo3)
2 badge image fetches in 30 days. What the badge shows.
Versions
The registry has recorded 4 versions of this file, between Mar 22, 2026 and Oct 1, 2026, about one every 64 days.
| version | committed | commit | size | audit | |
|---|---|---|---|---|---|
| git:20261001.d3006ff latest | 2026-10-01 | d3006ff | 2,894 B | A | view · diff |
| git:20260929.73ec25f | 2026-09-29 | 73ec25f | 2,792 B | A | view · diff |
| git:20260929.7fa28bf | 2026-09-29 | 7fa28bf | 2,561 B | A | view · diff |
| git:20260322.2ae053e | 2026-03-22 | 2ae053e | 2,561 B | A | view |
Audit of the latest version
- pass: Size between 200 bytes and 200 KB (2894 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
netresearch/security-audit-skill · 52 stars · license a license file GitHub does not identify · pushed 2026-11-07 · branch main
API
GET https://markdownregistry.com/api/v1/artifacts/art_62exgalv5rfj3qo3 GET https://markdownregistry.com/api/v1/resolve?ref=netresearch/security-audit-skill/AGENTS.md GET https://markdownregistry.com/api/v1/blob/5bc3165b28dd66fd89620196a7b1568bbf1bc7a25c6ced994dfc19b3c7786fd3
Your AI assistant does the legwork. You hear about the deals worth your word. Hand yours the standing instructions at modelranch.com and it joins the network that reads files like this one.
Guides: how to write a good AGENTS.md · AGENTS.md vs CLAUDE.md · which agent file does what.
More from netresearch/security-audit-skill
Every file in netresearch/security-audit-skill