security SKILL.md skillA

This file is byte-identical to the first copy the registry indexed, one of 3 indexed copies. Same content hash, so the same checks give both the same grade.

security from crewrig/crewrig is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.

mdr add crewrig/crewrig/security@git:20260620.d7282ed

Pins git:20260620.d7282ed in mdr.lock. Pin the fingerprint instead.

Audit grade

A, 17 of 17 checks passed

Kind

SKILL.md skill

Repository

crewrig/crewrig

Path

.agents/skills/security/SKILL.md

Versions recorded

1

Latest version

git:20260620.d7282ed, committed Jun 20, 2026

Size

4,238 bytes

Repository stars

24

License

Apache-2.0

Security review skill for threat modeling, dependency audit, secret hygiene, and code review through a security lens. Activate when a change touches authentication, authorization, secrets, cryptography, input parsing, deserialization, network calls, or upgrades to dependencies.

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

# Security

A focused review skill, not an exhaustive checklist. The goal is to
catch the realistic next exploit — not to enumerate the OWASP Top 10
every time.

## When to activate

Mandatory triggers:

- Authentication, authorization, or session-handling code changes.
- Secret / credential / token storage or transmission paths.
- Cryptographic primitive use (hashing, signing, encryption, RNG).
- External input parsing (HTTP bodies, CLI args, file uploads, IPC).
- Deserialization of untrusted data.
- Outbound network calls (URLs from user input, redirects, SSRF surface).
- Dependency additions or upgrades touching the surface above.

Optional but encouraged: any code review on a security-adjacent module
(payment, PII, audit log) — even when the diff itself looks innocuous.

## Operating mode

### 1. Trust boundary first

Before reading the diff, draw the trust boundary in your head:

- What input is **untrusted** here? (User input, network, file from
  another process, env var passed in by the user.)
- What is **inside** the boundary? (Internal config, signed messages,
  vetted constants.)
- The bug class to look for is the one that *crosses* the boundary
…

Read the whole file at its exact version.

How to install

mdr add crewrig/crewrig/security@sha256:6cd8033ab43e19c6

[![mdr](https://markdownregistry.com/badge/art_kwhdavijbzinffwz.svg)](https://markdownregistry.com/a/art_kwhdavijbzinffwz)

Versions

The registry has recorded 1 version of this file, committed on Jun 20, 2026.

Audit of the latest version

Source

API

GET https://markdownregistry.com/api/v1/artifacts/art_kwhdavijbzinffwz
GET https://markdownregistry.com/api/v1/resolve?ref=crewrig/crewrig/security
GET https://markdownregistry.com/api/v1/blob/6cd8033ab43e19c6b019fc8d7040ee23e7313afc80c81ed4ff5d728b98a58049

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: the SKILL.md format and its required fields · what to check before you install a skill · how to pin a skill to an exact version · where to find agent skills · keeping a team on the same skills · which agent file does what.

More from crewrig/crewrig

Every file in crewrig/crewrig

Other files named security

Browse by kind, by grade A, or by owner.