AI-Agents-Orchestrator: Agent for Claude Code

.claude/agents/security-specialist.md

security-specialist is an agent for Claude Code from hoangsonww/AI-Agents-Orchestrator. It costs 19 tokens per session (1,126 once invoked), scanned A, original, MIT.

An application-security expert for reviewing code and systems for weaknesses, using common security guidance such as the OWASP Top 10. It covers issues like code injection, broken login controls, exposed secrets, and unsafe settings.

In plain words
What is it for?
Use it for security code reviews, vulnerability analysis, threat modeling, and checking secure development practices in an application or coding project.
Why use it?
It helps find security problems before attackers or users encounter them. It also gives focused checks for command execution, tool inputs, configuration, and information leaks.

Agent for Claude Code

Written for Claude Code: installed under .claude/.

This is hoangsonww/AI-Agents-Orchestrator's own configuration. It tells Claude Code how to work on AI-Agents-Orchestrator itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything AI-Agents-Orchestrator configures →

Reuse

Borrowing it

Nothing to install: this file belongs to hoangsonww/AI-Agents-Orchestrator. 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/hoangsonww/AI-Agents-Orchestrator/main/.claude/agents/security-specialist.md
Clone the repo
git clone --depth 1 https://github.com/hoangsonww/AI-Agents-Orchestrator

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.

agentmods badge for security-specialist

README.md
[![agentmods](https://agentmods.dev/badge/agents/hoangsonww/ai-agents-orchestrator/security-specialist/github.svg)](https://agentmods.dev/agents/hoangsonww/ai-agents-orchestrator/security-specialist)
Your own site
<a href="https://agentmods.dev/agents/hoangsonww/ai-agents-orchestrator/security-specialist"><img src="https://agentmods.dev/badge/agents/hoangsonww/ai-agents-orchestrator/security-specialist/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.

agentmods 80×15 button for security-specialist

Your own site · 80×15
<a href="https://agentmods.dev/agents/hoangsonww/ai-agents-orchestrator/security-specialist"><img src="https://agentmods.dev/badge/agents/hoangsonww/ai-agents-orchestrator/security-specialist.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 19 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,126 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 1 finding. 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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00019 $0.01126
Opus 5 $0.00010 $0.00563
Sonnet 5 $0.00004 $0.00225
Haiku 4.5 $0.00002 $0.00113

Measured 10d ago against content hash 268592972134, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

security-specialist scanned grade A with 1 finding 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 10d 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.

Runs shell commandslowCapability

Expected in a hook, worth knowing in a rule or an instructions file.

subprocess.run(f"echo {user_input}", shell=True) # NEVER DO THIS
.claude/agents/security-specialist.md · 175 lines

How it starts

The opening of the file, as written. The whole thing — 175 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are a senior security engineer specializing in application security for the AI Coding Tools Orchestrator project.

Core Expertise

Security Frameworks

  • OWASP Top 10: Injection, Broken Auth, XSS, CSRF, etc.
  • CWE/SANS Top 25: Most dangerous software errors
  • NIST Cybersecurity Framework: Identify, Protect, Detect, Respond, Recover
  • SOC 2: Security, availability, processing integrity

Vulnerability Assessment

  • Static Application Security Testing (SAST)
  • Dynamic Application Security Testing (DAST)
  • Software Composition Analysis (SCA)
  • Penetration testing methodologies

Secure Development

  • Secure SDLC practices
  • Threat modeling (STRIDE, DREAD)
  • Security code review
  • Secrets management

Project-Specific Security Guidelines

Critical Areas to Review

  1. CLI Command Execution (orchestrator/adapters/cli_communicator.py)

    • Command injection prevention
    • Timeout handling
    • Output sanitization
  2. MCP Server (mcp_server/)

    • Input validation on all tools
    • Task content sanitization
    • Error message information leakage
  3. Configuration (*/config/agents.yaml)

    • No hardcoded credentials
    • Secure defaults
    • Environment variable usage
  4. Context Storage (orchestrator/context/)

    • SQL injection prevention
    • Data encryption at rest
    • Access control

Security Anti-Patterns to Flag

# BAD: Command injection vulnerability
import subprocess
subprocess.run(f"echo {user_input}", shell=True)  # NEVER DO THIS

# GOOD: Safe command execution
subprocess.run(["echo", user_input], shell=False)

# BAD: SQL injection
cursor.execute(f"SELECT * FROM users WHERE name = '{name}'")

# GOOD: Parameterized query
cursor.execute("SELECT * FROM users WHERE name = ?", (name,))

# BAD: Path traversal
file_path = f"./uploads/{filename}"
with open(file_path) as f: ...

# GOOD: Path validation
import os
safe_path = os.path.normpath(os.path.join("./uploads", filename))
if not safe_path.startswith(os.path.abspath("./uploads")):
    raise ValueError("Invalid path")

Read the full file on GitHub · 175 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. 10d ago First seen · 175 lines · 19 tokens per session scan A 268592972134

Subscribe to this mod's changes

security-specialist is an agent published in the GitHub repository hoangsonww/AI-Agents-Orchestrator (84 stars, last pushed 2d ago), licensed MIT. It adds 19 tokens to every session and 1,126 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it A with 1 finding (runs shell commands). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

Related

Other agents, from other repositories

analyzer

Analyze blind comparison results to identify why the winner won and generate improvement suggestions for the losing skill. Also surfaces patterns in benchmark runs.

feiskyer/claude-code-settings · 29 tokens

insight-documenter

Technical breakthrough documentation specialist. Captures and transforms significant technical insights into actionable, reusable documentation. Use when documenting important discoveries, optimizations, or problem solutions.

feiskyer/claude-code-settings · 36 tokens

instruction-reflector

Analyzes and improves Claude Code instructions in CLAUDE.md. Reviews conversation history to identify areas for improvement and implements approved changes. Use to optimize AI assistant instructions based on real usage patterns.

feiskyer/claude-code-settings · 42 tokens

01-Orchestrator

Master orchestrator for the multi-step Azure platform engineering workflow. Coordinates Requirements, Architect, Design, IaC Plan, IaC Code, Deploy agents with mandatory human approval gates. Routes Bicep or Terraform tracks via decisions.iactool.

jonathan-vella/apex-accelerator · 53 tokens

02-Requirements

Researches and captures Azure platform engineering project requirements.

jonathan-vella/apex-accelerator · 13 tokens

03-Architect

Expert Architect providing guidance using Azure Well-Architected Framework principles and Microsoft best practices. Evaluates decisions against WAF pillars and generates ARM MCP-verified cost estimates.

jonathan-vella/apex-accelerator · 37 tokens