crypto-audit

crypto-audit is a command for coding agents from HermeticOrmus/LibreSecOps-Claude-Code. It costs 0 tokens per session (1,368 once invoked), scanned A, original, MIT.

A command for reviewing how an application uses cryptography, including algorithms, keys, passwords, TLS, and tokens.

In plain words
What is it for?
Use it to audit source code, TLS or encryption configuration, architecture diagrams, and key-management documentation, either broadly or for a specific area.
Why use it?
It helps find weak algorithms, unsafe encryption settings, exposed keys, and poor key-management practices before they create security problems.

Command

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 commands/hermeticormus/libresecops-claude-code/crypto-audit
Clone the repo
git clone --depth 1 https://github.com/HermeticOrmus/LibreSecOps-Claude-Code

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 crypto-audit

README.md
[![agentmods](https://agentmods.dev/badge/commands/hermeticormus/libresecops-claude-code/crypto-audit.svg)](https://agentmods.dev/commands/hermeticormus/libresecops-claude-code/crypto-audit)
Your own site
<a href="https://agentmods.dev/commands/hermeticormus/libresecops-claude-code/crypto-audit"><img src="https://agentmods.dev/badge/commands/hermeticormus/libresecops-claude-code/crypto-audit.svg" alt="Measured on agentmods" height="20"></a>
Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,368 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 $0.01368
Opus 5 $0.00000 $0.00684
Sonnet 5 $0.00000 $0.00274
Haiku 4.5 $0.00000 $0.00137

Measured 3d ago against content hash c3281bbf9960, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

crypto-audit 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.

plugins/cryptography-essentials/commands/crypto-audit.md · 147 lines

How it starts

The opening of the file, as written. The whole thing — 147 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/crypto-audit

Audit cryptographic implementations for algorithm selection, key management, and implementation errors.

Trigger

Use when you need to:

  • Review cryptographic algorithm choices in application code
  • Audit password hashing implementations
  • Evaluate encryption-at-rest or encryption-in-transit configurations
  • Check for hardcoded keys, weak algorithms, or insecure modes
  • Assess TLS/SSL configuration
  • Review JWT token implementation
  • Evaluate key management practices

Input

One or more of:

  • Application code: Source code using cryptographic libraries
  • Configuration files: TLS configs (nginx, Apache, HAProxy), encryption configs
  • Architecture documentation: Data flow diagrams showing where encryption is applied
  • Key management documentation: Key storage, rotation, and access control policies
  • Specific scope: Focus area (e.g., "password hashing", "TLS only", "encryption at rest")

Process

Phase 1: Algorithm Assessment

  1. Symmetric encryption

    • Algorithm: AES-128/256 or ChaCha20 (acceptable), DES/3DES/RC4/Blowfish (unacceptable)
    • Mode: GCM or ChaCha20-Poly1305 (AEAD, correct), CBC without HMAC (vulnerable to padding oracle), ECB (broken for all practical purposes)
    • Nonce/IV: Generated with CSPRNG, never reused with the same key (GCM nonce reuse is catastrophic)
  2. Asymmetric encryption and signing

    • RSA key size: >= 2048 bits (acceptable), >= 3072 bits (recommended for new systems)
    • RSA padding: OAEP for encryption (correct), PKCS#1 v1.5 (vulnerable to Bleichenbacher), PSS for signatures (correct)
    • ECC: P-256 or P-384 (NIST curves), Curve25519/Ed25519 (modern preferred)
  3. Hashing

    • General purpose: SHA-256 or SHA-3 (correct), MD5 or SHA-1 (broken for collision resistance)
    • Password hashing: Argon2id (best), bcrypt (good), scrypt (good), PBKDF2-SHA256 (acceptable)
    • Password hashing with SHA-256/MD5/SHA-1 alone (CRITICAL -- not a password hash)
  4. Key derivation

    • HKDF for deriving subkeys from a master key
    • Argon2id or PBKDF2 for password-to-key derivation
    • Custom key derivation (likely insecure)

Read the full file on GitHub · 147 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. 3d ago First seen · 147 lines · 0 tokens per session scan A c3281bbf9960

Subscribe to this mod's changes

crypto-audit is a command published in the GitHub repository HermeticOrmus/LibreSecOps-Claude-Code (4 stars, last pushed 3mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 1,368 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.