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/file-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 | $0.00028 | $0.00720 |
| Opus 5 | $0.00014 | $0.00360 |
| Sonnet 5 | $0.00006 | $0.00144 |
| Haiku 4.5 | $0.00003 | $0.00072 |
Grade A, and why
file-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 — 76 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Detection Targets
| Type | Description | CWE |
|---|---|---|
| path-traversal | パストラバーサル | CWE-22 |
| arbitrary-file-upload | 任意ファイルアップロード | CWE-434 |
| lfi | ローカルファイルインクルージョン | CWE-98 |
| unrestricted-file-access | 制限なしファイルアクセス | CWE-552 |
Dangerous Patterns
patterns:
# Path Traversal (CWE-22)
- 'file_get_contents\s*\(\s*\$_(GET|POST|REQUEST)'
- 'fopen\s*\(\s*\$_(GET|POST|REQUEST)'
- 'readfile\s*\(\s*\$_(GET|POST|REQUEST)'
- 'open\s*\(\s*request\.(args|form)'
- 'fs\.readFile\s*\(\s*req\.(query|body)'
# Arbitrary File Upload (CWE-434)
- 'move_uploaded_file\s*\('
- '\$_FILES\s*\['
- 'request\.files'
- 'multer\('
# LFI (CWE-98)
- 'include\s*\(\s*\$_(GET|POST|REQUEST)'
- 'require\s*\(\s*\$_(GET|POST|REQUEST)'
- 'include_once\s*\(\s*\$_(GET|POST|REQUEST)'
- 'require_once\s*\(\s*\$_(GET|POST|REQUEST)'
# Unrestricted File Access (CWE-552)
- 'X-Sendfile'
- 'X-Accel-Redirect'
- 'send_file\s*\('
- 'res\.sendFile\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=FILE, types=path-traversal|arbitrary-file-upload|lfi|unrestricted-file-access
Severity Criteria
| Severity | Criteria |
|---|---|
| critical | Path traversal with direct user input to file operations |
| critical | Arbitrary file upload without extension/MIME validation |
| critical | LFI with direct user input to include/require |
| high | Unrestricted file access via X-Sendfile/X-Accel-Redirect |
| medium | File operations with partial validation |
CWE/OWASP Mapping
| Reference | ID |
|---|---|
| CWE | CWE-22: Improper Limitation of a Pathname |
| CWE | CWE-434: Unrestricted Upload of File with Dangerous Type |
| CWE | CWE-98: Improper Control of Filename for Include |
| CWE | CWE-552: Files or Directories Accessible to External Parties |
| OWASP Top 10 | A01:2025 Broken Access Control |
| OWASP Top 10 | A05:2025 Injection |
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 · 76 lines · 28 tokens per session scan A a87bf51ed449
file-attacker is an agent published in the GitHub repository morodomi/dev-crew (1 stars, last pushed 3d ago), licensed MIT. It adds 28 tokens to every session and 720 once invoked, about $0.0001 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.