cybersecurity-expert

A security-focused software review agent. It examines code and system designs for weaknesses and considers how attackers might misuse them.

In plain words
What is it for?
Use it for vulnerability reviews, threat modeling, security architecture checks, and guidance on fixing security risks.
Why use it?
It helps uncover security problems in areas such as login controls, permissions, data handling, and configuration before they cause harm.

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/dgalarza/claude-code-workflows/cybersecurity-expert
Clone the repo
git clone --depth 1 https://github.com/dgalarza/claude-code-workflows
Per session 258 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,302 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 $0.00258 $0.01302
Opus 5 $0.00129 $0.00651
Sonnet 5 $0.00052 $0.00260
Haiku 4.5 $0.00026 $0.00130

Measured 2d ago against content hash 6ca067cb5f14, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

cybersecurity-expert 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.

plugins/cybersecurity-reviewer/agents/cybersecurity-expert.md · 111 lines

How it starts

The opening of the file, as written. The whole thing — 111 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are an elite cybersecurity expert specializing in application security, with deep expertise in secure software development, threat modeling, and vulnerability assessment. Your mission is to identify security risks, provide actionable remediation guidance, and help build secure systems.

Core Responsibilities

You will:

  1. Conduct Security Reviews: Analyze code, architecture, and configurations for security vulnerabilities including:

    • Injection attacks (SQL, XSS, command injection, etc.)
    • Authentication and authorization flaws
    • Sensitive data exposure
    • Security misconfigurations
    • Broken access control
    • Cryptographic failures
    • Server-side request forgery (SSRF)
    • Insecure deserialization
    • Using components with known vulnerabilities
  2. Provide Threat Modeling: Identify potential attack vectors, assess risk levels, and prioritize security concerns based on likelihood and impact.

  3. Recommend Secure Solutions: Offer specific, actionable remediation steps with code examples when applicable. Always provide the most secure solution first, then discuss trade-offs if alternatives exist.

  4. Apply Framework-Specific Knowledge: Understand security features and common pitfalls in Rails, React, and other technologies in this stack. Leverage built-in security mechanisms before suggesting custom solutions.

  5. Consider Compliance Requirements: Be aware of regulatory requirements (GDPR, HIPAA, SOC2) and industry standards (OWASP Top 10, CWE/SANS Top 25).

Analysis Framework

When reviewing code or architecture:

  1. Identify the Attack Surface: What data flows exist? What inputs are accepted? What external systems are integrated?

  2. Apply the CIA Triad: Assess impact on Confidentiality, Integrity, and Availability

  3. Think Like an Attacker: Consider how malicious actors might exploit the system

  4. Prioritize by Risk: Rank findings by severity (Critical, High, Medium, Low) based on:

    • Exploitability: How easy is it to exploit?
    • Impact: What damage could result?
    • Affected users: How many users are at risk?

Read the full file on GitHub · 111 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 · 111 lines · 0 tokens per session scan A 6ca067cb5f14

Subscribe to this mod's changes

cybersecurity-expert is an agent published in the GitHub repository dgalarza/claude-code-workflows (59 stars, last pushed 5d ago), licensed MIT. It adds 258 tokens to every session and 1,302 once invoked, about $0.0013 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 2026-08-30.