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/ssrf-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 | $0.00033 | $0.00762 |
| Opus 5 | $0.00016 | $0.00381 |
| Sonnet 5 | $0.00007 | $0.00152 |
| Haiku 4.5 | $0.00003 | $0.00076 |
Grade C, and why
ssrf-attacker scanned grade C with 2 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.
Cloud metadata endpointhighServer-side request forgery
One request to 169.254.169.254 can return temporary IAM credentials.
| critical | Cloud metadata service access (169.254.169.254) | Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
- 'urllib\.request\.urlopen\s*\(\s*request\.' How it starts
The opening of the file, as written. The whole thing — 78 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Detection Targets
| Type | Description | Pattern |
|---|---|---|
| ssrf | ユーザー入力URLへのリクエスト | Direct URL from user input |
| blind-ssrf | レスポンス非表示のSSRF | Response not returned to user |
| partial-ssrf | URL一部のみユーザー制御 | Path/query controlled by user |
Dangerous Patterns
patterns:
# PHP - SSRF
- 'file_get_contents\s*\(\s*\$_(GET|POST|REQUEST)'
- 'curl_setopt\s*\([^,]+,\s*CURLOPT_URL\s*,\s*\$'
- 'fopen\s*\(\s*\$_(GET|POST|REQUEST)'
# Python - SSRF
- 'requests\.(get|post|put|delete|head)\s*\(\s*request\.'
- 'urllib\.request\.urlopen\s*\(\s*request\.'
- 'httpx\.(get|post)\s*\(\s*request\.'
# Node.js - SSRF
- 'axios\.(get|post)\s*\(\s*req\.(query|body|params)'
- 'fetch\s*\(\s*req\.(query|body|params)'
- 'http\.request\s*\(\s*req\.'
- 'got\s*\(\s*req\.(query|body|params)'
# Java - SSRF
- 'new\s+URL\s*\(\s*request\.getParameter'
- 'HttpURLConnection.*request\.getParameter'
- 'RestTemplate.*request\.getParameter'
# Cloud Metadata Services
- '169\.254\.169\.254'
- 'metadata\.google\.internal'
- 'metadata\.azure\.com'
- 'X-aws-ec2-metadata-token'
# Dangerous Protocol Schemes
- '\b(file|gopher|dict|ldap|tftp)://'
- 'localhost|127\.0\.0\.1|0\.0\.0\.0|::1'
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=SSRF, types=ssrf|blind-ssrf|partial-ssrf
Severity Criteria
| Severity | Criteria |
|---|---|
| critical | Full URL control with response returned to user |
| critical | Cloud metadata service access (169.254.169.254) |
| high | Blind SSRF - no response but request is made |
| medium | Partial URL control (path/query only) |
| low | URL parsing without request execution |
CWE/OWASP Mapping
| Reference | ID |
|---|---|
| CWE | CWE-918: Server-Side Request Forgery (SSRF) |
| OWASP Top 10 | A10:2021 Server-Side Request Forgery |
| OWASP Top 10 | A01:2025 Broken Access Control (as CWE-918) |
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 · 78 lines · 33 tokens per session scan C 4998c497aef6
ssrf-attacker is an agent published in the GitHub repository morodomi/dev-crew (1 stars, last pushed 3d ago), licensed MIT. It adds 33 tokens to every session and 762 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it C with 2 findings (cloud metadata endpoint, makes network calls). 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.