security-expert

A security review agent focused on application security, secure coding, vulnerability checks, and infrastructure-management risks. It reviews areas such as input validation, authentication, secrets, and secure APIs.

In plain words
What is it for?
Use it to review code and configuration for vulnerabilities, check authentication and API security, protect secrets, validate inputs, and assess security-related logging and errors.
Why use it?
It helps identify unsafe handling of user input, credentials, sensitive output, encryption, certificates, and security events before those mistakes 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/filthyrake/damens_mcps/security-expert
Clone the repo
git clone --depth 1 https://github.com/filthyrake/damens_mcps
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 2,360 The whole file, excluding the scripts and references it only reads on demand.
Security scan B 3 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 $0.02360
Opus 5 $0.00000 $0.01180
Sonnet 5 $0.00000 $0.00472
Haiku 4.5 $0.00000 $0.00236

Measured yesterday against content hash 518787608837, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade B, and why

security-expert scanned grade B with 3 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 yesterday.

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.

Asks for rootlowPrivilege escalation

A mod that escalates privileges can change anything on the machine, not only the project.

chmod 600 .env

Downgraded: this mod is about security review, or the phrase is quoted, so it is likely naming the pattern rather than instructing it.

Recursive force deletemediumDestructive command

rm -rf with a variable or a broad path is one typo away from removing the wrong tree.

malicious = "host; rm -rf /"

Downgraded: this mod is about security review, or the phrase is quoted, so it is likely naming the pattern rather than instructing it.

Runs shell commandslowCapability

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

os.system(f"ping {hostname}")
.github/agents/security-expert.md · 389 lines

How it starts

The opening of the file, as written. The whole thing — 389 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Security Review Agent

Agent Profile

Name: Security Review Expert
Expertise: Application security, secure coding practices, vulnerability assessment
Focus Areas: Input validation, authentication, secrets management, secure APIs

Specialization

This agent specializes in reviewing code and configurations for security vulnerabilities in the MCP servers collection. It focuses on infrastructure management security where mistakes can have serious consequences.

Critical Security Rules

Never Do These Things

  1. NEVER commit credentials - .env, config.json, API keys, passwords
  2. NEVER expose sensitive data - in logs, error messages, or responses
  3. NEVER trust user input - always validate and sanitize
  4. NEVER use weak encryption - no MD5, SHA1, weak algorithms
  5. NEVER ignore SSL/TLS - always verify certificates in production

Always Do These Things

  1. ALWAYS validate inputs - type check, range check, format check
  2. ALWAYS use environment variables - for credentials and secrets
  3. ALWAYS use HTTPS - for all API communications
  4. ALWAYS handle errors securely - don't leak internal details
  5. ALWAYS log security events - authentication, authorization failures

Security Review Checklist

Authentication & Authorization

# ❌ BAD - Hardcoded credentials
api_key = "1234567890abcdef"
password = "admin123"

# ✅ GOOD - From environment
api_key = os.getenv("API_KEY")
if not api_key:
    raise ValueError("API_KEY not set")

# ❌ BAD - No validation
def delete_vm(vm_id):
    api.delete(f"/vms/{vm_id}")

# ✅ GOOD - Check permissions
def delete_vm(vm_id, user_id):
    if not has_permission(user_id, "vm:delete", vm_id):
        raise PermissionError("Not authorized")
    api.delete(f"/vms/{vm_id}")

Input Validation

# ❌ BAD - No validation
def set_hostname(hostname):
    system.set_hostname(hostname)

# ✅ GOOD - Comprehensive validation
def set_hostname(hostname: str) -> None:
    """Set system hostname with validation."""
    # Type check
    if not isinstance(hostname, str):
        raise TypeError("hostname must be string")
    
    # Length check
    if len(hostname) > 253:
        raise ValueError("hostname too long")
    
    # Format check (RFC 1123)
    if not re.match(r'^[a-z0-9]([-a-z0-9]*[a-z0-9])?$', hostname):
        raise ValueError("invalid hostname format")
    
    system.set_hostname(hostname)

Read the full file on GitHub · 389 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. yesterday First seen · 389 lines · 0 tokens per session scan B 518787608837

Subscribe to this mod's changes

security-expert is an agent published in the GitHub repository filthyrake/damens_mcps (2 stars, last pushed 8d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 2,360 tokens. A static security scan graded it B with 3 findings (asks for root, recursive force delete, runs shell commands). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Related

Other agents, from other repositories

Demonstrate

Agent for demonstrating VS Code features.

microsoft/vscode · 10 tokens

playwright-test-generator

Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.

microsoft/playwright · 151 tokens

.NET-Notebook-Migration-Agent

Expert .NET and documentation transformation agent that migrates Polyglot Jupyter notebooks into clean Markdown and companion .NET sample code.

microsoft/ai-agents-for-beginners · 33 tokens

AVM Owner Triage

Triage open GitHub issues across the Azure Verified Modules (AVM) repos an owner maintains. Splits the backlog into a Copilot-delegatable pile and a human pile, produces a report with a delegation ratio, and never comments or assigns without explicit user approval.

github/awesome-copilot · 61 tokens

Ultimate Transparent Thinking Beast Mode

Agent "Ultimate Transparent Thinking Beast Mode" from github/awesome-copilot, covering quantum cognitive architecture, phase 2: adversarial intelligence & red-team analysis, phase 3: implementation & iterative refinement and phase 4: comprehensive verification & completion.

github/awesome-copilot · 11 tokens

code-reviewer

Performs thorough code reviews for the Notebooks in the Cookbook repo, focusing on Python/Jupyter best practices, and project-specific standards. Use this agent proactively after writing any significant code changes, especially when modifying notebooks, Github Actions, and scripts.

anthropics/claude-cookbooks · 52 tokens