Security Rules

Security Rules is an agent for coding agents from JSK9999/ai-nexus. It costs 13 tokens per session (410 once invoked), scanned A, original, Apache-2.0.

Security rules for protecting secrets and preventing common web and software vulnerabilities. They cover sensitive data, input handling, authentication, authorization, encryption, and security checks.

In plain words
What is it for?
Use them when writing or reviewing code, logs, endpoints, database queries, configuration, authentication, dependencies, or deployment settings.
Why use it?
They reduce the risk of exposing credentials or introducing attacks such as injection, cross-site scripting, or request forgery.

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/jsk9999/ai-nexus/security-rules
Clone the repo
git clone --depth 1 https://github.com/JSK9999/ai-nexus

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 Rules

README.md
[![agentmods](https://agentmods.dev/badge/agents/jsk9999/ai-nexus/security-rules.svg)](https://agentmods.dev/agents/jsk9999/ai-nexus/security-rules)
Your own site
<a href="https://agentmods.dev/agents/jsk9999/ai-nexus/security-rules"><img src="https://agentmods.dev/badge/agents/jsk9999/ai-nexus/security-rules.svg" alt="Measured on agentmods" height="20"></a>
Per session 13 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 410 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 $0.00013 $0.00410
Opus 5 $0.00006 $0.00205
Sonnet 5 $0.00003 $0.00082
Haiku 4.5 $0.00001 $0.00041

Measured 3d ago against content hash 9954a63e103c, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

Security Rules 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 3d 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.

config/agents/security-rules.md · 52 lines

What it actually says

Security Rules

ABSOLUTE Rules (NEVER Violate)

NEVER

  • Leave secrets (passwords/API keys/tokens) in code/logs/tickets/environment variables/.env files.
  • Log sensitive data (PII/credit cards/SSN) in logs.
  • Leave SQL injection, XSS, CSRF vulnerabilities.
  • Commit secrets, API keys, tokens, or sensitive information.

ALWAYS

  • Validate, normalize, and encode all inputs; use parameterized queries.
  • Use HTTPS/TLS and apply principle of least privilege.
  • Apply authentication/authorization to all endpoints.
  • Set security headers (CSP, HSTS, X-Frame-Options).
  • Regularly scan and update dependency vulnerabilities.

Security Violation Protocol

Stop work immediately and request review upon security violations.

Pre-commit Security Checklist

  • No secrets (passwords/API keys/tokens) in code
  • No sensitive data (PII/credit cards/SSN) in logs
  • No SQL injection vulnerabilities
  • No XSS vulnerabilities
  • No CSRF vulnerabilities
  • All inputs validated and sanitized
  • Parameterized queries used for database operations
  • Authentication/authorization applied to endpoints
  • Development debug code removed
  • Console logs cleaned up

Common Vulnerability Prevention

Vulnerability Prevention
SQL Injection Use parameterized queries, ORMs
XSS Encode output, use CSP headers
CSRF Use CSRF tokens, SameSite cookies
Auth Bypass Validate on server, check permissions
Data Exposure Minimize data, encrypt at rest/transit
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. 3d ago First seen · 52 lines · 13 tokens per session scan A 9954a63e103c

Subscribe to this mod's changes

Security Rules is an agent published in the GitHub repository JSK9999/ai-nexus (18 stars, last pushed 5mo ago), licensed Apache-2.0. It adds 13 tokens to every session and 410 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.