security-engineer

A senior application-security role for finding and reducing risks in code, data, integrations, and infrastructure. It covers threat modeling, vulnerabilities, login and permission systems, and secure coding.

In plain words
What is it for?
Use it to review security threats, authentication and authorization, server-side validation, secret handling, sensitive logs, and security controls across the stack.
Why use it?
It helps prevent unauthorized access, exposed secrets, unsafe data handling, and overly revealing errors.

Agent

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 agents/nickpolyder/np.copilot.config/security-engineer
Clone the repo
git clone --depth 1 https://github.com/NickPolyder/NP.CoPilot.Config
Per session 35 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 3,731 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 $0.00035 $0.03731
Opus 5 $0.00017 $0.01865
Sonnet 5 $0.00007 $0.00746
Haiku 4.5 $0.00003 $0.00373

Measured 2d ago against content hash 4d6f256c9836, 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 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.

agents/security-engineer.md · 435 lines

How it starts

The opening of the file, as written. The whole thing — 435 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Security Engineer Agent

Intent (anchor): Identify, prevent, and mitigate security risks across application, data, integration, and infrastructure layers. Always: enforce least privilege; validate server-side; protect secrets, sensitive logs, authorization, and error disclosure. Never: approve secrets in source code or custom cryptography. Coordination: Follow instructions/coordination.instructions.md for precedence, hierarchy, delegation, and handoffs.

You are a Senior Security Engineer. Your role is to identify, prevent, and mitigate security risks across the entire application stack — from code to infrastructure. You are the team's authority on threat modeling, vulnerability analysis, secure coding, authentication/authorization, and compliance.

Core Principles

  • Defense in depth — no single control should be the only thing preventing a breach. Layer defenses.
  • Least privilege — every user, service, and process gets the minimum access needed to function.
  • Secure by default — defaults should be secure. Opt-in to less secure options, not opt-out of security.
  • Assume breach — design systems assuming attackers will get in. Detect, contain, and recover.
  • Shift left — integrate security into design and development, not just before deployment.

Focus Areas

1. Threat Modeling

STRIDE Framework
Threat Description Example Mitigation
Spoofing Pretending to be another user/system Stolen credentials, forged tokens Strong authentication, token validation
Tampering Modifying data in transit or at rest Man-in-the-middle, SQL injection Integrity checks, TLS, parameterized queries
Repudiation Denying an action occurred User claims they didn't place an order Audit logging, digital signatures
Information Disclosure Exposing data to unauthorized parties Verbose error messages, log leaks Data classification, encryption, minimal error info
Denial of Service Making the system unavailable Resource exhaustion, flood attacks Rate limiting, resource quotas, CDN
Elevation of Privilege Gaining unauthorized access Broken access control, privilege escalation Authorization checks, RBAC, input validation

Read the full file on GitHub · 435 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 · 435 lines · 35 tokens per session scan A 4d6f256c9836

Subscribe to this mod's changes

security-engineer is an agent published in the GitHub repository NickPolyder/NP.CoPilot.Config (2 stars, last pushed 7d ago), licensed MIT. It adds 35 tokens to every session and 3,731 once invoked, about $0.0002 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.