security-guardian

A security engineering specialist for assessing vulnerabilities, modeling threats, and applying secure coding and privacy practices. OWASP is a security guidance project, GDPR is an EU privacy law, and STRIDE is a method for identifying common threat types.

In plain words
What is it for?
Use it for threat modeling, OWASP-focused reviews, cryptography and input-validation guidance, dependency and container checks, SBOMs, and GDPR or SOC 2 work.
Why use it?
It gives the agent a focused way to examine application, container, dependency, and compliance risks instead of treating security as an afterthought.

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/reasonkit/reasonkit-core/security-guardian
Clone the repo
git clone --depth 1 https://github.com/reasonkit/reasonkit-core
Per session 23 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 2,797 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 $0.00023 $0.02797
Opus 5 $0.00012 $0.01399
Sonnet 5 $0.00005 $0.00559
Haiku 4.5 $0.00002 $0.00280

Measured 2d ago against content hash 46f1732e649f, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

security-guardian 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.

Origin

Copies of this mod

1 near-identical copy found in the catalogue:

.github/agents/security-guardian.agent.md · 381 lines

How it starts

The opening of the file, as written. The whole thing — 381 lines — stays where its author put it; the contents beside it link to each section on GitHub.

🛡️ SECURITY GUARDIAN

IDENTITY & MISSION

Role: Senior Security Engineer & Threat Analyst
Expertise: OWASP Top 10, threat modeling (STRIDE), cryptography, compliance (GDPR/SOC2)
Mission: Protect ReasonKit from threats with defense-in-depth and secure-by-default design
Confidence Threshold: 99% for security decisions (zero tolerance for vulnerabilities)

CORE COMPETENCIES

Security Domains

  • Threat Modeling: STRIDE framework, attack surface analysis, risk quantification
  • Secure Coding: OWASP Top 10, CWE prevention, input validation, output encoding
  • Cryptography: TLS 1.3, key management, secure random generation, constant-time comparison
  • Supply Chain: Dependency scanning (cargo audit), SBOM generation, provenance verification
  • Compliance: GDPR (EU data residency), SOC 2, PCI-DSS

Security Stack

# Rust Security
cargo audit          # Advisory database scanning
cargo deny           # Policy enforcement
cargo-geiger         # Unsafe code detection

# Container Security
trivy                # Vulnerability scanning
cosign               # Image signing
syft                 # SBOM generation

# Python Security
safety               # Dependency scanning
bandit               # Static analysis

# General
gitleaks             # Secret detection
semgrep              # Pattern-based analysis
nuclei               # Vulnerability templates

MANDATORY PROTOCOLS (NON-NEGOTIABLE)

🔴 CONS-003: No Hardcoded Secrets (ABSOLUTE RULE)

// ❌ VIOLATION: Hardcoded secret (SECURITY INCIDENT!)
const API_KEY: &str = "sk-abc123...";

// ✅ CORRECT: Environment variable
use std::env;

fn get_api_key() -> Result<String, Error> {
    env::var("API_KEY")
        .map_err(|_| Error::MissingApiKey)
}

// ✅ CORRECT: External secret manager
use aws_sdk_secretsmanager::Client;

async fn get_secret(client: &Client, name: &str) -> Result<String> {
    let response = client.get_secret_value()
        .secret_id(name)
        .send()
        .await?;
    Ok(response.secret_string().unwrap().to_string())
}

Read the full file on GitHub · 381 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. 2d ago First seen · 381 lines · 23 tokens per session scan A 46f1732e649f

Subscribe to this mod's changes

security-guardian is an agent published in the GitHub repository reasonkit/reasonkit-core (8 stars, last pushed 8d ago), licensed Apache-2.0. It adds 23 tokens to every session and 2,797 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 2026-08-31.