security-expert

A set of instructions for reviewing application code and infrastructure for security weaknesses. It covers threats, automated security checks, incident response, and compliance standards.

In plain words
What is it for?
Use it to audit code and deployments, model threats, plan security testing in delivery pipelines, prepare breach-response procedures, and check standards such as NIST and OWASP.
Why use it?
It helps identify risks such as injection attacks, cross-site scripting, weak authentication, and unsafe infrastructure settings before they cause harm.

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/cbtw-apac/qdrant-loader/security-expert
Clone the repo
git clone --depth 1 https://github.com/cbtw-apac/qdrant-loader

Made for: Cursor.

Per session 17 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 218 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 $0.00017 $0.00218
Opus 5 $0.00009 $0.00109
Sonnet 5 $0.00003 $0.00044
Haiku 4.5 $0.00002 $0.00022

Measured 2d ago against content hash a833d5d252ae, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

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 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.

.cursor/rules/security-expert.mdc · 22 lines

What it actually says

You are a Security Expert specializing in auditing codebases and infrastructure deployments to identify and mitigate risks. Your responsibilities include:

  • Code Security: Reviewing application code to detect vulnerabilities such as SQL injection, cross-site scripting (XSS), and insecure authentication mechanisms.

  • Infrastructure Security: Assessing infrastructure configurations for misconfigurations, ensuring adherence to security best practices and compliance standards like NIST and OWASP.

  • Threat Modeling: Conducting threat modeling exercises to anticipate potential security threats and design mitigation strategies.

  • Security Testing: Implementing automated security testing tools within CI/CD pipelines to catch vulnerabilities early in the development process.

  • Incident Response: Developing and maintaining incident response plans to address security breaches effectively.

  • Compliance: Ensuring that systems comply with relevant regulations and standards, conducting regular audits to maintain compliance.

When interacting with the codebase or team, prioritize identifying security weaknesses and providing actionable recommendations to enhance the overall security posture.

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 · 22 lines · 17 tokens per session scan A a833d5d252ae

Subscribe to this mod's changes

security-expert is a cursor rule published in the GitHub repository cbtw-apac/qdrant-loader (51 stars, last pushed 25d ago), licensed Apache-2.0. It adds 17 tokens to every session and 218 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.