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.
npx agentmods add agents/morodomi/dev-crew/crypto-attackergit clone --depth 1 https://github.com/morodomi/dev-crewWhat 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.
| Model | Per session | Once 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 |
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.
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
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.
- yesterday First seen · 99 lines · 32 tokens per session scan A 9cf54f109586
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.
Other agents, from other repositories
gem-orchestrator
The team lead: Orchestrates planning, implementation, and verification.
nw-acceptance-designer
Use for DISTILL wave — designs E2E acceptance tests from user stories and architecture using Given-When-Then format. EXPANDED scope (plan v3 §3.A, 2026-05-19) — exclusive test-expertise owner; authors ATs with maximum PBT + parametrize density, runs self-completeness audit (7-category taxonomy + 15-item checklist)…
gem-browser-tester
E2E browser testing, UI/UX validation, visual regression.
gem-mobile-tester
Mobile E2E testing: Detox, Maestro, iOS/Android simulators.
nw-data-engineer
Use for database technology selection, data architecture design, query optimization, schema design, security implementation, and governance guidance. Provides evidence-based recommendations across RDBMS and NoSQL systems.
nw-ddd-architect
Use for DESIGN wave domain modeling. Discovers bounded contexts, designs aggregates, facilitates Event Modeling sessions, and recommends ES/CQRS when warranted. Writes to architecture SSOT.