security

A set of security rules for designing and building software before implementation. It covers risks such as unauthorised access, unsafe network requests, harmful dependencies, private data exposure, and unsafe AI output.

In plain words
What is it for?
It helps threat-model features involving authentication, personal or payment data, uploads, outbound requests, dependencies, webhooks, queues, or AI output used by software.
Why use it?
It makes security decisions before a feature widens the attack surface, reducing the chance that serious weaknesses are discovered only after the feature is built.

Skill for Claude CodeCodex

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

agentmods
npx agentmods add skills/prabhdeepsingh/claude-plugins/security
Any agent
npx skills add PrabhdeepSingh/claude-plugins --skill security
Clone the repo
git clone --depth 1 https://github.com/PrabhdeepSingh/claude-plugins

Made for: Claude Code, Codex.

Per session 102 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,427 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5 $0.00102 $0.02427
Opus 5 $0.00051 $0.01213
Sonnet 5 $0.00020 $0.00485
Haiku 4.5 $0.00010 $0.00243

Measured 2d ago against content hash 4a608961731d, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

security scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

sonu/skills/security/SKILL.md · 94 lines

How it starts

The opening of the file, as written. The whole thing — 94 lines — stays where its author put it; the contents beside it link to each section on GitHub.

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.


1. Threat-model first — five minutes, before any control

Before choosing defenses, name what's being defended. Three steps, time-boxed to minutes not meetings:

  • Map the trust boundaries — every place outside data enters: HTTP requests, form fields, file uploads, webhooks, third-party API responses, queue messages, and LLM output (it's derived from inputs you don't control, so it's a boundary like any other).
  • Name the assets — credentials, PII, payment data, admin capabilities, money movement. A boundary matters in proportion to what's reachable through it.
  • Write abuse cases next to use cases. For each feature ask "how would I misuse this?" — then make that abuse the first test you write ([[tdd]]'s bug-fix reflex, applied before the bug exists). "Upload a profile photo" pairs with "upload a 2GB file", "upload an SVG with a script tag", "upload to someone else's profile".

Read the full file on GitHub · 94 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 2d ago First seen · 94 lines · 102 tokens per session scan A 4a608961731d

Subscribe to this mod's changes

security is a skill published in the GitHub repository PrabhdeepSingh/claude-plugins (3 stars, last pushed 2d ago), licensed MIT. It adds 102 tokens to every session and 2,427 once invoked, about $0.0005 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Related

Other skills, from other repositories

dummy-dataset

Generate realistic dummy datasets for testing with customizable columns, constraints, and output formats (CSV, JSON, SQL, Python script). Use when creating test data, building mock datasets, or generating sample data for development and demos.

phuryn/pm-skills · 48 tokens

outcome-roadmap

Transform an output-focused roadmap into an outcome-focused one that communicates strategic intent. Rewrites initiatives as outcome statements reflecting user and business impacts. Use when shifting to outcome roadmaps, making a roadmap more strategic, or rewriting feature lists as outcomes.

phuryn/pm-skills · 53 tokens

retro

Facilitate a structured sprint retrospective — what went well, what didn't, and prioritized action items with owners and deadlines. Use when running a retrospective, reflecting on a sprint, creating action items from team feedback, or learning how to run effective retros.

phuryn/pm-skills · 52 tokens

release-notes

Generate user-facing release notes from tickets, PRDs, or changelogs. Creates clear, engaging summaries organized by category (new features, improvements, fixes). Use when writing release notes, creating changelogs, announcing product updates, or summarizing what shipped.

phuryn/pm-skills · 57 tokens

shipping-artifacts

The durable documentation set that makes an AI-built (vibe-coded) app reviewable before shipping. A small core every app needs — architecture, user/permission flows, permissions, variables/secrets, and a test-coverage map — plus conditional docs added only when they apply: emails, scheduled work, SEO, and embedded…

phuryn/pm-skills · 120 tokens

competitive-battlecard

Create sales-ready competitive battlecards comparing your product against a specific competitor — positioning, feature comparison, objection handling, and win/loss patterns. Use when preparing sales teams, creating competitive materials, or responding to 'why not competitor X?'.

phuryn/pm-skills · 52 tokens