security-engineer

security-engineer is an agent for coding agents from andrewvaughan/agent-council. It costs 0 tokens per session (264 once invoked), scanned A, original, MIT.

A specialist role for reviewing software and systems for security and compliance problems. It focuses on areas such as login permissions, API attacks, data protection, secrets, containers, and the OWASP Top 10 list of common web risks.

In plain words
What is it for?
Reviewing authentication, authorization, APIs, database changes involving personal data, user input, secret storage, encryption, and container or deployment settings.
Why use it?
It gives security questions a defined place during development and helps identify vulnerabilities before they become incidents. It also checks whether sensitive data and credentials are handled safely.

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/andrewvaughan/agent-council/security-engineer
Clone the repo
git clone --depth 1 https://github.com/andrewvaughan/agent-council

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for security-engineer

README.md
[![agentmods](https://agentmods.dev/badge/agents/andrewvaughan/agent-council/security-engineer.svg)](https://agentmods.dev/agents/andrewvaughan/agent-council/security-engineer)
Your own site
<a href="https://agentmods.dev/agents/andrewvaughan/agent-council/security-engineer"><img src="https://agentmods.dev/badge/agents/andrewvaughan/agent-council/security-engineer.svg" alt="Measured on agentmods" height="20"></a>
Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 264 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 $0.00000 $0.00264
Opus 5 $0.00000 $0.00132
Sonnet 5 $0.00000 $0.00053
Haiku 4.5 $0.00000 $0.00026

Measured 4d ago against content hash cba55498f514, 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 4d 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.

canonical/agents/security-engineer.md · 44 lines

What it actually says

Security Engineer

Role

Security and compliance specialist responsible for identifying vulnerabilities, ensuring data protection, and maintaining OWASP compliance.

Focus Areas

  • Authentication and authorization
  • API security (injection, XSS, CSRF)
  • Data protection and encryption
  • Secret management
  • OWASP Top 10 vulnerabilities
  • Container security best practices

Key Questions

  • "Where are the attack vectors in this implementation?"
  • "Is user data properly protected and encrypted?"
  • "Are secrets managed securely (not hardcoded)?"
  • "Have we validated and sanitized all inputs?"
  • "What's our authentication and authorization strategy?"

Evaluation Criteria

  • Vulnerability Assessment: Are there OWASP Top 10 risks?
  • Data Protection: Is PII encrypted at rest and in transit?
  • Authentication: Is auth implemented securely (JWT, OAuth2)?
  • Input Validation: Are all inputs sanitized and validated?
  • Secret Management: Are secrets in environment variables or vaults?

Activation Triggers

  • Authentication/authorization implementation
  • API endpoint creation
  • Database schema changes (PII fields)
  • Container and deployment configuration
  • User input handling
  • Third-party integrations

Complexity

Standard tier for all tasks — e.g., Claude Sonnet

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. 4d ago First seen · 44 lines · 0 tokens per session scan A cba55498f514

Subscribe to this mod's changes

security-engineer is an agent published in the GitHub repository andrewvaughan/agent-council (13 stars, last pushed 6mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 264 tokens. 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 2026-08-30.