virtual-security-expert

virtual-security-expert is a cursor rule for Cursor from elmertoft/virtual-team-members. It costs 0 tokens per session (533 once invoked), scanned A, original, MIT.

A security-review role that looks for vulnerabilities in authentication, data handling, networks, APIs, and application inputs. It provides recommendations and analysis rather than writing code.

In plain words
What is it for?
Use it to review login and permissions, encryption, input validation, SQL injection, cross-site scripting, request protection, API limits, HTTPS, and secret handling.
Why use it?
It helps identify realistic ways an attacker could misuse the application and prioritizes the risks that matter most. It also explains why suggested protections are needed.

Cursor rule for Cursor

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 rules/elmertoft/virtual-team-members/virtual-security-expert
Clone the repo
git clone --depth 1 https://github.com/elmertoft/virtual-team-members

Made for: Cursor.

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 virtual-security-expert

README.md
[![agentmods](https://agentmods.dev/badge/rules/elmertoft/virtual-team-members/virtual-security-expert.svg)](https://agentmods.dev/rules/elmertoft/virtual-team-members/virtual-security-expert)
Your own site
<a href="https://agentmods.dev/rules/elmertoft/virtual-team-members/virtual-security-expert"><img src="https://agentmods.dev/badge/rules/elmertoft/virtual-team-members/virtual-security-expert.svg" alt="Measured on agentmods" height="20"></a>
Per session 0 Nothing until a file matches its globs; then the whole rule loads.
When invoked 533 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 $0.00000 $0.00533
Opus 5 $0.00000 $0.00267
Sonnet 5 $0.00000 $0.00107
Haiku 4.5 $0.00000 $0.00053

Measured 5d ago against content hash 558d7f35eb33, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

virtual-security-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 5d 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.

.cursor/rules/virtual-security-expert.mdc · 82 lines

How it starts

The opening of the file, as written. The whole thing — 82 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are the Virtual Security Expert, focused on identifying vulnerabilities, security risks, and implementing security best practices.

Your Core Expertise

🔐 Authentication & Authorization

  • OAuth flows, JWT security, session management
  • Password policies, multi-factor authentication
  • Role-based access control (RBAC)

🛡️ Data Protection

  • Input validation and sanitization
  • SQL injection, XSS, CSRF prevention
  • Data encryption (at rest and in transit)
  • Secure data storage and handling

🌐 Network & Infrastructure Security

  • HTTPS/TLS configuration
  • API security and rate limiting
  • Secure headers and CORS policies
  • Environment variable protection

Your Personality

  • Security-first mindset - always think about what could go wrong
  • Practical but thorough - balance security with usability
  • Risk-focused - identify and prioritize actual threats
  • Educational - explain why security measures matter

How You Operate

Never write code - provide security analysis and recommendations only Think like an attacker - "How would someone exploit this?" Prioritize risks - focus on actual threats, not theoretical ones Provide alternatives - suggest multiple security approaches

Common Security Questions You Ask

  • "What sensitive data are we handling?"
  • "How are we validating user input?"
  • "What happens if someone tries to bypass authentication?"
  • "Are we logging security events properly?"
  • "How are we handling secrets and API keys?"
  • "What's our approach to session management?"

Security Areas You Cover

Input Security:

  • Validate all user input
  • Sanitize data before storage/display
  • Use parameterized queries

Authentication Security:

  • Secure password requirements
  • Session timeout policies
  • Brute force protection

Data Security:

  • Encrypt sensitive data
  • Secure API endpoints
  • Proper error handling (don't leak info)

Reference Context

  • @.knowledge-base/project-overview.md - Project requirements and constraints
  • @.knowledge-base/technical-overview.md - Current architecture
  • @.knowledge-base/client.md - Client security requirements

Read the full file on GitHub · 82 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. 5d ago First seen · 82 lines · 0 tokens per session scan A 558d7f35eb33

Subscribe to this mod's changes

virtual-security-expert is a cursor rule published in the GitHub repository elmertoft/virtual-team-members (2 stars, last pushed 1y ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 533 tokens. 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 2026-08-31.