crypto-attacker

A code-scanning agent for finding insecure settings and weak cryptography. It checks for issues such as enabled debugging, outdated hash functions, weak encryption methods, default passwords, and unrestricted cross-origin access.

In plain words
What is it for?
Use it to inspect Laravel, Django, Flask, and Express code for debug settings, MD5 or SHA-1 usage, weak cryptography, default credentials, and permissive CORS configuration.
Why use it?
These mistakes can expose application details, weaken password or data protection, or let untrusted websites access an application. The agent detects listed patterns in several common frameworks.

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/morodomi/dev-crew/crypto-attacker
Clone the repo
git clone --depth 1 https://github.com/morodomi/dev-crew
Per session 32 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 986 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 $0.00032 $0.00986
Opus 5 $0.00016 $0.00493
Sonnet 5 $0.00006 $0.00197
Haiku 4.5 $0.00003 $0.00099

Measured yesterday against content hash 9cf54f109586, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

crypto-attacker 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 yesterday.

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.

agents/crypto-attacker.md · 99 lines

How it starts

The opening of the file, as written. The whole thing — 99 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Detection Targets

Type Description Pattern
debug-enabled デバッグモード有効 DEBUG = True, APP_DEBUG = true
weak-hash 弱いハッシュ関数 md5(, sha1(
weak-crypto 弱い暗号アルゴリズム DES, RC4, ECB, Blowfish
default-credentials デフォルト認証情報 admin/admin, root/root
insecure-cors 危険なCORS設定 Access-Control-Allow-Origin: *

Framework Detection Patterns

Framework Vulnerable Pattern Safe Pattern
Laravel APP_DEBUG=true, config('app.debug') APP_DEBUG=false
Django DEBUG = True, hashlib.md5 DEBUG = False, hashlib.sha256
Flask app.debug = True app.debug = False
Express cors(), cors({origin: '*'}) cors({origin: 'https://...'})

Dangerous Patterns

patterns:
  # Debug Enabled (CWE-489)
  - 'DEBUG\s*=\s*True'
  - 'APP_DEBUG\s*=\s*true'
  - 'debug:\s*true'
  - 'app\.debug\s*=\s*[Tt]rue'

  # Weak Hash (CWE-328)
  - 'md5\s*\('
  - 'sha1\s*\('
  - 'hashlib\.md5'
  - 'hashlib\.sha1'
  - 'MessageDigest\.getInstance\s*\(\s*["\']MD5["\']'
  - 'MessageDigest\.getInstance\s*\(\s*["\']SHA-?1["\']'

  # Weak Crypto (CWE-327)
  - 'DES\.'
  - 'DES/'
  - 'RC4'
  - 'ECB'
  - 'Blowfish'
  - 'PKCS1Padding'
  - 'Cipher\.getInstance\s*\(["\']DES'
  - 'Cipher\.getInstance\s*\(["\'].*ECB'

  # Default Credentials (CWE-1392)
  - 'admin["\']?\s*[,:]\s*["\']?admin'
  - 'root["\']?\s*[,:]\s*["\']?root'
  - 'password["\']?\s*[,:]\s*["\']?password'
  - 'user["\']?\s*[,:]\s*["\']?user'

  # Insecure CORS (CWE-942)
  - 'Access-Control-Allow-Origin:\s*\*'
  - 'CORS_ALLOW_ALL\s*=\s*[Tt]rue'
  - 'CORS_ORIGIN_ALLOW_ALL\s*=\s*[Tt]rue'
  - 'cors\s*\(\s*\)'
  - "origin:\s*['\"]\\*['\"]"

Output

Base: {metadata: {scan_id, scanned_at, agent}, vulnerabilities: [{id, type, vulnerability_class, cwe_id, severity, file, line, code, description, remediation}], summary: {total, critical, high, medium, low}} Extra: prefix=CRYPTO, types=debug-enabled|weak-hash|weak-crypto|default-credentials|insecure-cors

Read the full file on GitHub · 99 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. yesterday First seen · 99 lines · 32 tokens per session scan A 9cf54f109586

Subscribe to this mod's changes

crypto-attacker is an agent published in the GitHub repository morodomi/dev-crew (1 stars, last pushed 3d ago), licensed MIT. It adds 32 tokens to every session and 986 once invoked, about $0.0002 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.