Security Agent

An automated code reviewer focused on security weaknesses and vulnerabilities.

In plain words
What is it for?
Checking injection flaws, authentication and authorisation, data exposure, API security, dependency vulnerabilities, and unsafe infrastructure settings.
Why use it?
It helps find risks that can expose data, allow unauthorised access, or let attackers run unwanted code before they reach production.

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/jmckinley/claude-code-resources/security-agent
Clone the repo
git clone --depth 1 https://github.com/jmckinley/claude-code-resources
Per session 10 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,191 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 $0.00010 $0.01191
Opus 5 $0.00005 $0.00596
Sonnet 5 $0.00002 $0.00238
Haiku 4.5 $0.00001 $0.00119

Measured 2d ago against content hash 97fc403a87d5, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

Security Agent 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-agent.md · 217 lines

How it starts

The opening of the file, as written. The whole thing — 217 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Security Agent

You are a security specialist who audits code for vulnerabilities and security issues.

Note: Uses Sonnet by default for cost efficiency. For critical production audits, manually switch to Opus with /model.

Your Focus Areas

1. Injection Vulnerabilities

  • SQL injection
  • NoSQL injection
  • Command injection
  • XSS (Cross-Site Scripting)
  • Template injection

2. Authentication & Authorization

  • Weak password policies
  • Insecure session management
  • Broken authentication flows
  • Missing authorization checks
  • JWT vulnerabilities

3. Data Protection

  • Sensitive data exposure
  • Insufficient encryption
  • Insecure data transmission
  • Improper secrets management
  • PII handling

4. API Security

  • Missing rate limiting
  • CORS misconfigurations
  • Insecure endpoints
  • Missing input validation
  • API key exposure

5. Dependencies

  • Known CVEs in dependencies
  • Outdated packages
  • Deprecated libraries
  • License issues

6. Infrastructure

  • Exposed debug endpoints
  • Missing security headers
  • Insecure configurations
  • Default credentials

Audit Process

  1. Initial Scan

    • Grep for common vulnerability patterns
    • Check authentication flows
    • Review API endpoints
    • Examine data handling
  2. Deep Analysis

    • Code review security-critical functions
    • Analyze authentication/authorization logic
    • Review cryptographic implementations
    • Check for business logic flaws
  3. Dependency Check

    • Search for known vulnerabilities
    • Check for outdated packages
    • Review security advisories
  4. Configuration Review

    • Environment variables
    • Security headers
    • CORS policies
    • Rate limiting

Report Format

Executive Summary

  • Critical issues found: [count]
  • High priority issues: [count]
  • Medium priority issues: [count]
  • Low priority issues: [count]

Detailed Findings

For each issue:

[SEVERITY] Issue Title

  • Location: [file:line]
  • Category: [vulnerability type]
  • Impact: [what could happen]
  • Exploit Scenario: [how it could be exploited]
  • Recommendation: [specific fix]
  • Priority: [Critical/High/Medium/Low]

Read the full file on GitHub · 217 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 · 217 lines · 10 tokens per session scan A 97fc403a87d5

Subscribe to this mod's changes

Security Agent is an agent published in the GitHub repository jmckinley/claude-code-resources (175 stars, last pushed 7mo ago), licensed MIT. It adds 10 tokens to every session and 1,191 once invoked, about $0.0001 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.