security SKILL.md skillA
security from prabhdeepsingh/claude-plugins is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.
mdr add prabhdeepsingh/claude-plugins/security@git:20260913.4e5ade4Pins git:20260913.4e5ade4 in mdr.lock. Pin the fingerprint instead.
- Audit grade
- A, 17 of 17 checks passed
- Kind
- SKILL.md skill
- Repository
- prabhdeepsingh/claude-plugins
- Path
sonu/skills/security/SKILL.md- Versions recorded
- 2
- Latest version
- git:20260913.4e5ade4, committed Sep 13, 2026
- First version recorded
- Aug 26, 2026
- Size
- 12,268 bytes
- Repository stars
- 4
- License
- MIT
Build-time security discipline — threat-model before controls, Always/Ask-First/Never boundary tiers, SSRF, supply chain, LLM/agent security, privacy. INVOKE PROACTIVELY when building anything touching auth, user data, uploads, outbound fetches, dependencies, or model output — even when nobody says "security". The after-the-fact review pass belongs to /security-review; validation mechanics: [[code-standards]]; infra secrets: [[infra-standards]].
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 — decide what can go wrong before deciding what to build Security added after the design is a patch; security added at build time is a property. The cheapest moment to prevent a vulnerability is while the trust boundaries are still being drawn — before the upload handler exists, before the fetch reaches the network, before the dependency is installed. These rules make that moment explicit: name what can go wrong, gate the changes that widen the attack surface, and treat the classes of failure that recur everywhere — retried secrets, poisoned packages, model output in a sink — as design constraints, not review findings. ## When to apply this Any feature touching authentication or authorization, personal or payment data, file uploads, outbound requests to user-influenced destinations, new dependencies, webhooks or queues, or LLM/agent output feeding anything executable. The scoped mechanics stay with their owners — parameterized queries and boundary validation in [[code-standards]] §9, secret storage and CI credentials in [[infra-standards]] §3/§5 — this skill owns the decisions those mechanics assume were already made. --- …
Read the whole file at its exact version.
How to install
mdr add prabhdeepsingh/claude-plugins/security@sha256:d501a85eff88d7eaThe line at the top of this page pins the label git:20260913.4e5ade4, 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_sbinm3frrpyf5b73)
3 badge image fetches in 30 days. What the badge shows.
Versions
The registry has recorded 2 versions of this file, between Aug 26, 2026 and Sep 13, 2026, about one every 17 days.
| version | committed | commit | size | audit | |
|---|---|---|---|---|---|
| git:20260913.4e5ade4 latest | 2026-09-13 | 4e5ade4 | 12,268 B | A | view · diff |
| git:20260826.a9147da | 2026-08-26 | a9147da | 11,380 B | A | view |
Audit of the latest version
- pass: Frontmatter block present
- pass: Frontmatter declares a name
- pass: Frontmatter declares a description
- pass: Size between 200 bytes and 200 KB (12268 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
prabhdeepsingh/claude-plugins · 4 stars · license MIT · pushed 2026-10-27 · branch main
API
GET https://markdownregistry.com/api/v1/artifacts/art_sbinm3frrpyf5b73 GET https://markdownregistry.com/api/v1/resolve?ref=prabhdeepsingh/claude-plugins/security GET https://markdownregistry.com/api/v1/blob/d501a85eff88d7ea8eecf28914b1d26ab5ae99f5846d82c24a8200e38efb1424
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 prabhdeepsingh/claude-plugins
Every file in prabhdeepsingh/claude-plugins