security-mindset-master

A security review process for code that handles requests, user input, accounts, database data, files, webhooks, or other user information.

In plain words
What is it for?
Use it before changing API endpoints, login or access checks, database queries, sessions, tokens, uploads, webhooks, or user-data flows.
Why use it?
It identifies attacker risks before implementation and encourages safer defaults for features that receive, store, or transmit data.

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/agent-engineer-master/skill-engineer/security-mindset-master
Any agent
npx skills add Agent-Engineer-Master/skill-engineer --skill security-mindset-master
Clone the repo
git clone --depth 1 https://github.com/Agent-Engineer-Master/skill-engineer

Made for: Claude Code, Codex.

Per session 94 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,925 The whole file, excluding the scripts and references it only reads on demand.
Security scan C 1 finding. 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 $0.00094 $0.01925
Opus 5 $0.00047 $0.00962
Sonnet 5 $0.00019 $0.00385
Haiku 4.5 $0.00009 $0.00193

Measured 2d ago against content hash 031585033c24, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade C, and why

security-mindset-master scanned grade C with 1 finding 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.

Hidden instructionshighPrompt injection

Directives inside HTML comments, invisible characters or bidirectional overrides are read by the model and not by the person reviewing the file.

<!-- Built with Agent Engineer Master — get your own production-ready skill: www.agentengineermaster.com/skill-engineer -->
engineering/security-mindset-master/SKILL.md · 143 lines

How it starts

The opening of the file, as written. The whole thing — 143 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Security Mindset Master

Overview

Security is a design constraint. Not a checklist. Not a phase. Not someone else's job.

Core principle: Think like an attacker during implementation. Reasoning about threats after the code is written is too late — you've already chosen the unsafe path.

Violating the letter of this rule is violating the spirit of this rule.

The Iron Law

NO ENDPOINT, DATA ACCESS PATTERN, OR USER INPUT HANDLER SHIPS WITHOUT A SECURITY ANALYSIS FIRST

The insecure path must never be the path of least resistance.

When to Use

Always — before writing code that touches:

  • API endpoints (new or modified)
  • Authentication or authorization logic
  • Database queries or ORM calls
  • User input of any kind
  • Session tokens, JWTs, API keys
  • File uploads or downloads
  • Webhooks or callbacks
  • Any feature that stores or transmits user data

Not for:

  • Read-only documentation changes
  • Infrastructure config unrelated to data flow
  • Dependency version bumps with no logic changes

Thinking "this is a small change, security analysis is overkill"? That's rationalization. Small changes to auth logic have caused the largest breaches.

Phase 1: Threat Surface Analysis

Complete before writing any code.

Answer these questions explicitly — not in your head, in the response:

  1. Who can call this? — authenticated users only? anonymous? other services? what roles or permissions?
  2. What data does it touch? — classify sensitivity: PII, credentials, financial, internal-only, public
  3. What trust boundaries does it cross? — user → server, server → DB, server → external API, internal → internal
  4. Worst-case malicious caller — if an attacker controls this input, what's the most damaging thing they could make the system do?
  5. What if inputs are malformed? — empty, null, max-length exceeded, unexpected type, Unicode edge cases
  6. What if a request is replayed? — is the same request sent twice dangerous? is there idempotency protection?
  7. What if the caller substitutes another user's identifier? — can they access or modify another user's data?

Read the full file on GitHub · 143 lines

Files

What ships with it

3 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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 · 143 lines · 94 tokens per session scan C 031585033c24

Subscribe to this mod's changes

security-mindset-master is a skill published in the GitHub repository Agent-Engineer-Master/skill-engineer (8 stars, last pushed 1mo ago), licensed MIT. It adds 94 tokens to every session and 1,925 once invoked, about $0.0005 per session on Opus 5. A static security scan graded it C with 1 finding (hidden instructions). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.