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/injection-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 | $0.00968 |
| Opus 5 | $0.00016 | $0.00484 |
| Sonnet 5 | $0.00006 | $0.00194 |
| Haiku 4.5 | $0.00003 | $0.00097 |
Grade A, and why
injection-attacker scanned grade A with 1 finding against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured yesterday.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Runs shell commandslowCapability
Expected in a hook, worth knowing in a rule or an instructions file.
| Subprocess | サブプロセス実行 | subprocess.call(), child_process.exec() | How it starts
The opening of the file, as written. The whole thing — 110 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Detection Targets
SQL Injection
| Type | Description | Pattern |
|---|---|---|
| Union-based | UNION SELECT攻撃 | 文字列結合でのSQL構築 |
| Error-based | エラーメッセージ利用 | 未処理の例外、エラー出力 |
| Boolean-blind | 条件分岐による推測 | 動的WHERE句構築 |
Command Injection
| Type | Description | Pattern |
|---|---|---|
| Direct execution | OSコマンド直接実行 | exec(), system()への入力連結 |
| Shell invocation | シェル経由実行 | shell_exec(), popen()への入力 |
| Subprocess | サブプロセス実行 | subprocess.call(), child_process.exec() |
Framework Detection Patterns
| Framework | Vulnerable Pattern | Safe Pattern |
|---|---|---|
| Laravel | DB::raw($input), whereRaw($input) |
DB::table()->where(), Eloquent ORM |
| Django | cursor.execute(f"...{input}") |
cursor.execute("...%s", [input]) |
| Flask | db.execute(f"...{input}") |
db.execute("...?", (input,)) |
| Express | query("SELECT..."+input) |
query("SELECT...?", [input]) |
Dangerous Patterns
patterns:
# SQL Injection
## PHP/Laravel
- 'DB::raw\s*\('
- 'whereRaw\s*\('
- '\$.*->query\s*\('
- 'mysql_query\s*\('
## Python/Django/Flask
- 'execute\s*\(\s*f["\']'
- 'execute\s*\(\s*["\'].*%'
- 'cursor\.execute\s*\([^,]+\)'
## Node.js/Express
- 'query\s*\(\s*[`"\'].*\+'
- 'query\s*\(\s*`.*\$\{'
# Command Injection
## PHP
- 'exec\s*\(\s*\$'
- 'shell_exec\s*\('
- 'system\s*\(\s*\$'
- 'passthru\s*\('
- 'popen\s*\('
- 'proc_open\s*\('
- '`.*\$.*`'
## Python
- 'os\.system\s*\('
- 'subprocess\.(call|Popen)\s*\('
- 'os\.popen\s*\('
## Node.js
- 'child_process\.(exec|spawn)\s*\('
- 'execSync\s*\('
## Go
- 'exec\.Command\s*\('
Safe Patterns
safe_patterns:
# PHP - framework standard
- 'Artisan::call'
- 'Process::run'
# Python - list form (safe)
- 'subprocess\.(call|run)\s*\(\s*\['
# Node.js - no variable
- 'execSync\s*\(\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=SQLI|CMD, types=union-based|error-based|boolean-blind|direct-execution|shell-invocation|subprocess
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 · 110 lines · 32 tokens per session scan A 44bdd0d40659
injection-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 968 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 1 finding (runs shell commands). 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.