security-engineer

Application and infrastructure security guidance for finding and preventing common weaknesses in software. It covers areas such as access control, login systems, web attacks, and protecting secrets.

In plain words
What is it for?
Use it to review OWASP Top 10 risks, JWTs, RBAC, OAuth, threat models, SSRF, CSRF, XSS, and secret management.
Why use it?
It helps identify security risks while designing and building software, instead of discovering them after a breach. It gives developers a structured way to consider what they protect, who might attack, and where attacks could enter.

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/code-saurabh/openskills/security-engineer
Any agent
npx skills add CODE-SAURABH/OpenSkills --skill security-engineer
Clone the repo
git clone --depth 1 https://github.com/CODE-SAURABH/OpenSkills

Made for: Claude Code, Codex.

Per session 47 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,436 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 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 $0.00047 $0.02436
Opus 5 $0.00023 $0.01218
Sonnet 5 $0.00009 $0.00487
Haiku 4.5 $0.00005 $0.00244

Measured yesterday against content hash b9f251bf6cbe, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

security-engineer scanned grade A 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 yesterday.

The scan reads SKILL.md. This mod also ships 1 executable file (scripts/scan_secrets.py), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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.

Runs shell commandslowCapability

Expected in a hook, worth knowing in a rule or an instructions file.

- Avoid `eval()`, `exec()`, `os.system()`, shell interpolation with user data
security-engineer/SKILL.md · 207 lines

How it starts

The opening of the file, as written. The whole thing — 207 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Security Engineering

Approach every security task as an engineer who has read real incident post-mortems and knows that most breaches are not exotic zero-days — they are OWASP Top 10 vulnerabilities that were known, understood, and skipped. Security is not a phase at the end of development. It is a design constraint applied from the first line of code.


Step 0: Threat Model Before You Build

Before writing security controls, understand what you are protecting:

  1. What are the assets? User data, credentials, financial records, proprietary algorithms — name them
  2. Who are the threat actors? External attackers, malicious insiders, compromised dependencies, misconfigured services
  3. What are the attack surfaces? API endpoints, authentication flows, file uploads, third-party integrations, admin interfaces
  4. What are the trust boundaries? Where does data cross from untrusted to trusted? Every boundary needs validation
  5. What is the impact of a breach? Data exposure, financial loss, regulatory penalty, reputational damage — prioritise controls by impact

Use STRIDE as a thinking tool: Spoofing, Tampering, Repudiation, Information disclosure, Denial of service, Elevation of privilege. For each component, ask which STRIDE categories apply.


OWASP Top 10 — Mandatory Defenses

A01 — Broken Access Control

  • Deny by default — every resource is protected unless explicitly made public
  • Verify ownership on every request — a user accessing /api/documents/123 must own document 123
  • Implement RBAC at the middleware layer — roles and permissions enforced before business logic runs
  • Never trust client-supplied IDs for access decisions without server-side verification
  • Log all access control failures — they are reconnaissance signals

A02 — Cryptographic Failures

  • Enforce HTTPS everywhere — redirect HTTP to HTTPS; HSTS header with long max-age
  • Encrypt sensitive data at rest — AES-256 minimum
  • Never store passwords in plaintext or with reversible encryption — bcrypt (cost ≥ 12) or argon2id
  • Never store credit card numbers, SSNs, or equivalent PII unless absolutely required — tokenise instead
  • Use strong, modern TLS — TLS 1.2 minimum, TLS 1.3 preferred; disable weak cipher suites

Read the full file on GitHub · 207 lines

Files

What ships with it

2 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. yesterday First seen · 207 lines · 47 tokens per session scan A b9f251bf6cbe

Subscribe to this mod's changes

security-engineer is a skill published in the GitHub repository CODE-SAURABH/OpenSkills (2 stars, last pushed 1mo ago), licensed MIT. It adds 47 tokens to every session and 2,436 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 1 finding (runs shell commands). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.