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/csrf-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 | $0.00035 | $0.01163 |
| Opus 5 | $0.00017 | $0.00581 |
| Sonnet 5 | $0.00007 | $0.00233 |
| Haiku 4.5 | $0.00003 | $0.00116 |
Grade A, and why
csrf-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 — 117 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Detection Targets
| Type | Description | Pattern |
|---|---|---|
| csrf-token-missing | CSRFトークン欠如 | フォームに@csrf/csrf_token等なし |
| csrf-protection-disabled | CSRF保護の意図的無効化 | @csrf_exempt, skip_verify等 |
| samesite-cookie-missing | SameSite Cookie未設定 | SameSite=None or 未指定 |
| state-change-unprotected | 状態変更操作の保護不備 | POST/PUT/DELETEにCSRF保護なし |
Framework Detection Patterns
| Framework | Vulnerable Pattern | Safe Pattern |
|---|---|---|
| Laravel | Form without @csrf | @csrf directive, VerifyCsrfToken middleware |
| Django | @csrf_exempt decorator | CsrfViewMiddleware, {% csrf_token %} |
| Flask | WTForms without csrf | CSRFProtect, validate_csrf() |
| Express | No csurf middleware | csurf(), csrf() middleware |
| Rails | skip_before_action :verify_authenticity_token | protect_from_forgery, csrf_meta_tags |
Dangerous Patterns
patterns:
# Laravel - CSRF token missing
- '<form[^>]{0,500}method\s*=\s*["\']?(POST|PUT|DELETE)["\']?[^>]{0,500}>'
- 'VerifyCsrfToken.{0,100}\$except'
# Django - CSRF protection disabled
- '@csrf_exempt'
- 'MIDDLEWARE\s*=\s*\[(?![^\]]*CsrfViewMiddleware)'
# Flask - No CSRF protection
- 'FlaskForm.{0,50}csrf.{0,20}False'
- 'WTF_CSRF_ENABLED\s*=\s*False'
# Express - No csurf middleware
- 'app\.(post|put|delete|patch)\s*\([^)]{1,200}\)'
- 'router\.(post|put|delete|patch)\s*\([^)]{1,200}\)'
# Rails - CSRF protection disabled
- 'skip_before_action\s*:verify_authenticity_token'
- 'protect_from_forgery.{0,50}except:'
# SameSite Cookie issues (only flag None without Secure)
- 'SameSite\s*=\s*None(?!.{0,30}Secure)'
- 'samesite\s*:\s*["\']none["\'](?!.{0,30}secure)'
# AJAX/REST API patterns
- 'fetch\s*\([^,]+,\s*\{[^}]*method:\s*["\']?(POST|PUT|DELETE|PATCH)'
- 'axios\.(post|put|delete|patch)\s*\('
- '\$\.(ajax|post)\s*\('
Safe Patterns
safe_patterns:
# Laravel
- '@csrf'
- 'csrf_field()'
- 'csrf_token()'
# Django
- '{% csrf_token %}'
- 'CsrfViewMiddleware'
# Flask
- 'CSRFProtect'
- 'validate_csrf'
# Express
- 'csurf()'
- 'csrf()'
# Rails
- 'protect_from_forgery'
- 'csrf_meta_tags'
# SameSite - safe
- 'SameSite\s*=\s*(Strict|Lax)'
- 'SameSite\s*=\s*None.{0,30}Secure'
# Custom header verification
- 'X-Requested-With'
- 'X-CSRF-Token'
- 'Authorization:\s*Bearer'
# Double-submit cookie pattern
- 'csrf.*cookie.*header'
- 'cookie.*csrf.*match'
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 · 117 lines · 35 tokens per session scan A d4902b508888
csrf-attacker is an agent published in the GitHub repository morodomi/dev-crew (1 stars, last pushed 3d ago), licensed MIT. It adds 35 tokens to every session and 1,163 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
browser-pilot
Playwright browser automation — navigate URLs, screenshot, interact with UI, check accessibility, capture console errors. Max 20 interactions. MUST close browser when done.
asset-creator
Creates code-based visual assets — SVG icons, OG image HTML, social banners, icon sets. Code-only output (not raster PNG/JPG). Use browser-pilot + screenshot for raster.
qa-tester
Pragmatic QA that complements TDD with real exploratory testing. Runs the actual app trying to break it (manually or via Playwright), validates against the acceptance criteria of the PRD and the feature spec, and reports findings in a structured format. Invoked between phases or before marking a feature as done. Does…
gem-mobile-tester
Mobile E2E testing: Detox, Maestro, iOS/Android simulators.
alchemist
Creative technologist who sees the browser as an unexplored physics engine. Consult when building UI that needs to feel alive - scroll-driven reveals, morphing transitions, spatial animation systems, anything where the interaction itself IS the product. Thinks in weight, tension, and breath before thinking in code.…
audit-geo
Evaluates AI crawler access, llms.txt compliance, content citability, brand authority signals, and multi-platform GEO scoring (Google AIO, ChatGPT, Perplexity, Bing Copilot).