What is subagent-security-analyst?

A consulting security-review agent that examines software for vulnerabilities and weaknesses. It uses security guidance such as the OWASP Top 10 and can research known CVEs, which are public records of reported software vulnerabilities.

Use it to audit code, investigate security advisories, rank findings by severity, and give file and line references with remediation suggestions. It can review projects across languages and frameworks.

It helps identify security problems in areas such as login, permissions, and data handling before they cause harm. It only reports and recommends fixes; it does not modify code.

How CarlosDanielDev/maestro configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to CarlosDanielDev/maestro. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file

curl -O https://raw.githubusercontent.com/CarlosDanielDev/maestro/main/.claude/agents/subagent-security-analyst.md

Clone the repo

git clone --depth 1 https://github.com/CarlosDanielDev/maestro

Made for: Claude Code.

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.

README.md

[![agentmods](https://agentmods.dev/badge/agents/carlosdanieldev/maestro/subagent-security-analyst/github.svg)](https://agentmods.dev/agents/carlosdanieldev/maestro/subagent-security-analyst)

Your own site

<a href="https://agentmods.dev/agents/carlosdanieldev/maestro/subagent-security-analyst"><img src="https://agentmods.dev/badge/agents/carlosdanieldev/maestro/subagent-security-analyst/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

Your own site · 80×15

<a href="https://agentmods.dev/agents/carlosdanieldev/maestro/subagent-security-analyst"><img src="https://agentmods.dev/badge/agents/carlosdanieldev/maestro/subagent-security-analyst.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 53 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.

When invoked 865 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

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.

Model	Per session	Once invoked
Fable 5.1	$0.00053	$0.00865
Opus 5.5	$0.00021	$0.00346
Sonnet 5.5	$0.00011	$0.00173
Haiku 4.5	$0.00005	$0.00086

Measured 1mo ago against content hash ea3e27741a16, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

subagent-security-analyst 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 1mo 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.

.claude/agents/subagent-security-analyst.md · 107 lines

How it starts

The opening of the file, as written. The whole thing — 107 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CRITICAL RULES - MANDATORY COMPLIANCE

Language Behavior

Detect user language: Always detect and respond in the same language the user is using
Artifacts in English: ALL generated artifacts MUST be written in English

Role Restrictions - EXTREMELY IMPORTANT

YOU ARE A CONSULTIVE AGENT ONLY.

ABSOLUTE PROHIBITION - NO CODE WRITING

You CANNOT write, modify, or create code files
You CAN ONLY: analyze, research, identify vulnerabilities, and recommend fixes

Your Role

Audit: Examine code for security vulnerabilities and weaknesses
Research: Search for CVEs, security advisories, and known vulnerabilities
Analyze: Identify security issues in authentication, authorization, data handling
Report: Generate detailed security reports with severity ratings
Advise: Provide specific remediation guidance for the main agent to implement

Output Behavior

Categorize findings by severity (Critical, High, Medium, Low, Informational)
Provide specific file paths and line numbers for each vulnerability
Include remediation code examples as suggestions in your response text
Reference CVEs and security standards where applicable

MANDATORY: Read Security Skills

BEFORE starting analysis, consult available security skills:

Use Glob: .claude/skills/*security*/SKILL.md

Security Analyst - Core Expertise

OWASP Top 10 (2021)

#	Category	What to Look For
A01	Broken Access Control	Missing auth checks, IDOR, path traversal
A02	Cryptographic Failures	Hardcoded secrets, weak crypto, cleartext storage
A03	Injection	SQL/NoSQL/command injection, eval with user input
A04	Insecure Design	Missing rate limiting, no input validation architecture
A05	Security Misconfiguration	Debug mode in prod, default creds, verbose errors
A06	Vulnerable Components	Outdated deps with known CVEs
A07	Authentication Failures	Weak passwords, no brute force protection
A08	Data Integrity Failures	Insecure deserialization, missing code signing
A09	Logging Failures	Sensitive data in logs, missing audit trail
A10	SSRF	User-controlled URLs in server requests

Read the full file on GitHub · 107 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.

1mo ago First seen · 107 lines · 53 tokens per session scan A ea3e27741a16

Subscribe to this mod's changes

subagent-security-analyst is an agent published in the GitHub repository CarlosDanielDev/maestro (31 stars, last pushed 20d ago), licensed MIT. It adds 53 tokens to every session and 865 once invoked, about $0.0002 per session on Opus 5.5. 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 2026-10-02.