agentmods.dev

security-lord

security-lord is a skill for Claude Code, Codex from m3taz-ahmed/ai-globals. It costs 0 tokens per session (1,103 once invoked), scanned A, original, MIT.

A security architecture guide covering application threats, encryption, secure connections, certificates, identity, networks, and compliance. It uses established security guidance such as OWASP, a widely used application-security reference.

In plain words
What is it for?
Use it to threat-model applications, choose cryptographic methods, configure TLS and certificates, design zero-trust access, and plan detection or compliance controls.
Why use it?
It helps structure security decisions and avoid unsafe cryptography, weak transport settings, over-trusted systems, and incomplete threat models.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

not rated 5repo changed 6d ago A scan 0 tokens original MIT

Good fit Use it to threat-model applications, choose cryptographic methods, configure TLS and certificates, design zero-trust access, and plan detection or compliance controls.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/m3taz-ahmed/ai-globals/security-lord
View source ↗ m3taz-ahmed/ai-globals
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.

Any agent
npx skills add m3taz-ahmed/ai-globals --skill security-lord
Clone the repo
git clone --depth 1 https://github.com/m3taz-ahmed/ai-globals

Made for: Claude Code, Codex.

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-lord

README.md
[![agentmods](https://agentmods.dev/badge/skills/m3taz-ahmed/ai-globals/security-lord/github.svg)](https://agentmods.dev/skills/m3taz-ahmed/ai-globals/security-lord)
Your own site
<a href="https://agentmods.dev/skills/m3taz-ahmed/ai-globals/security-lord"><img src="https://agentmods.dev/badge/skills/m3taz-ahmed/ai-globals/security-lord/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for security-lord

Your own site · 80×15
<a href="https://agentmods.dev/skills/m3taz-ahmed/ai-globals/security-lord"><img src="https://agentmods.dev/badge/skills/m3taz-ahmed/ai-globals/security-lord.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 0 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,103 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 5.1 $0.00000 $0.01103
Opus 5 $0.00000 $0.00551
Sonnet 5 $0.00000 $0.00221
Haiku 4.5 $0.00000 $0.00110

Measured 6d ago against content hash a07c5086ac18, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

security-lord 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 6d 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.

skills/security-lord/SKILL.md · 28 lines

How it starts

The opening of the file, as written. The whole thing — 28 lines — stays where its author put it; the contents beside it link to each section on GitHub.

[SKILL] security-lord [OBJ] Threat-model, choose crypto, configure TLS, design PKI, harden workloads, and secure AI agents and MCP infrastructure. [RULES]

  1. [CMD] IDs: OWASP cheatsheets /owasp/cheatsheetseries, OWASP Top 10 /owasp/top10, cryptography /pyca/cryptography, TLS/PKI /openssl/openssl.
  2. [REQ] Pillar coverage: app security, threat modeling, cryptography, transport security, PKI/identity, network/cloud security, zero-trust, detection/response, compliance/governance, AI/agent security.
  3. [REQ] Query relevant ID + topic (tls, x509, owasp, encryption, mcp, llm, agent).
  4. [REQ] OWASP Top 10 (web): audit all code against OWASP Top 10. Zero tolerance for unescaped inputs, broken access control, and cryptographic failures.
  5. [REQ] OWASP LLM Top 10 2026: audit against all 10 categories (published Aug 2026): LLM01 Prompt Injection (cross-modal + memory persistence), LLM02 Sensitive Information Disclosure, LLM03 Excessive Agency, LLM04 Supply Chain (model weights + MCP tool servers), LLM05 Data/Model Poisoning, LLM06 Unbounded Consumption, LLM07 Misinformation, LLM08 Hidden Context Exposure, LLM09 Vector/Embedding Weaknesses, LLM10 Improper Output Handling.
  6. [REQ] OWASP ASI Top 10 2026: audit against the separate Agentic Applications list. Key: ASI03 Identity & Privilege Abuse, ASI04 Agentic Supply Chain Vulnerabilities, ASI05 Unexpected Code Execution.
  7. [REQ] Cryptography: never recommend weak primitives (MD5, SHA1, DES, RSA <2048, CBC without MAC, unauthenticated encryption). Prefer AEAD (AES-GCM, ChaCha20-Poly1305) and modern curves (X25519, Ed25519, secp256k1).
  8. [REQ] TLS/PKI: enforce TLS 1.3 minimum. Zero-trust ties identity, device, network, and data controls. Certificate transparency, OCSP stapling, and short-lived certs preferred.
  9. [REQ] MCP security: audit MCP servers for tool poisoning (CVE-2025-54136, CVSS 8.8), session-ID injection (CVE-2026-52869), cross-client data leaks (CVE-2026-25536). Verify tool definitions are hash-pinned and re-validated on every list refresh. Enforce per-tool scopes.
  10. [REQ] SARC enforcement: verify 4 enforcement sites — Pre-Action Gate (block injection/PII/policy violations before LLM call), Action-Time Monitor (rate/cost/budget enforcement, circuit breakers), Post-Action Auditor (log, evaluate, score), Escalation Router (human approval, kill-switch, incident creation). All 4 must be present and active.
  11. [REQ] Agent SRE Governance: verify SLOs, error budgets, circuit breakers, chaos engineering, trace replay, Ed25519 artifact signing, SBOMs, and OpenTelemetry tracing for all agent deployments.
  12. [REQ] Model weight provenance: verify model weights have provenance metadata. Unsafe serialization (pickle) must be rejected. Use safe formats (safetensors, GGUF). AI/ML SBOMs required.
  13. [REQ] Rate-limiting layers: verify 3-layer gateway — token-bucket per (user, repo, model), circuit breaker per pattern, declarative fallback chain.
  14. [REQ] Network/cloud security: enforce network segmentation, least-privilege IAM, secrets management (no hardcoded credentials), and runtime threat detection for all workloads.
  15. [REQ] Detection/response: implement tamper-evident audit logging, anomaly detection, and incident response playbooks. EU AI Act Article 73: 15 days for ordinary serious incidents; 2 days for widespread infringement / critical infrastructure; 10 days for death.
  16. [REQ] Compliance/governance: align with ISO 42001, NIST AI RMF, and EU AI Act. Map security controls to MITRE ATLAS v2026.06, ATT&CK v19.1, CWE 4.20, and CSA AI Controls Matrix v1.
  17. [REQ] Cross-modal injection defense: audit for prompt injection via images, audio, and documents. Untrusted multimodal content must be sandboxed and separated from instructions.
  18. [REQ] Memory-persistence attacks: audit for hidden instructions that survive across turns. Memory stores must be taint-labeled and sanitized before persistence.
  19. [PROHIBIT] Deploying AI agents without OWASP LLM 2026 + ASI 2026 audit clearance and SARC 4-site enforcement.
  20. [PROHIBIT] Using MCP servers without hash-pinned tool definitions, CVE compliance verification, and per-tool scope enforcement.

Read the full file on GitHub · 28 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. 6d ago Changed · +15 lines a07c5086ac18
  2. 9d ago First seen · 13 lines · 0 tokens per session scan A 1f2edd676339

Subscribe to this mod's changes

security-lord is a skill published in the GitHub repository m3taz-ahmed/ai-globals (5 stars, last pushed yesterday), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 1,103 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 2026-09-03.

Security
Related

Other skills, from other repositories

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

local-ai-agents

Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…

microsoft/ai-agents-for-beginners · 200 tokens

next-cache-components-adoption

Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…

vercel/next.js · 95 tokens

chat-pet-sprite-creation

Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.

microsoft/vscode · 53 tokens

cpu-profile-analysis

Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…

microsoft/vscode · 71 tokens

insight-error-page

Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…

vercel/next.js · 83 tokens