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/xxe-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 | $0.00030 | $0.01145 |
| Opus 5 | $0.00015 | $0.00573 |
| Sonnet 5 | $0.00006 | $0.00229 |
| Haiku 4.5 | $0.00003 | $0.00114 |
Grade A, and why
xxe-attacker scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured yesterday.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 105 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Detection Targets
| Type | Description | Risk |
|---|---|---|
| classic-xxe | 外部エンティティによるファイル読み取り | High |
| blind-xxe | OOBデータ送信 | High |
| xxe-dos | Billion Laughs / Quadratic Blowup | Medium |
| ssrf-xxe | XXE経由のSSRF | High |
Framework Detection Patterns
| Language | Vulnerable Pattern | Safe Pattern |
|---|---|---|
| PHP | simplexml_load_string($input) |
libxml_disable_entity_loader(true) (PHP 7.x) |
| PHP | loadXML($input, LIBXML_NOENT) |
loadXML($input) without LIBXML_NOENT |
| Python | lxml.etree.parse(input) |
defusedxml.parse() |
| Python | xml.sax.parse(input) |
xml.etree.ElementTree (safe by default) |
| Java | DocumentBuilderFactory.newInstance() |
setFeature("external-general-entities", false) |
| Java | SAXParserFactory.newInstance() |
setFeature("external-parameter-entities", false) |
| Java | XMLReader.parse(input) |
setFeature("disallow-doctype-decl", true) |
| Node.js | libxmljs.parseXml(input) |
xml2js (safe by default) |
| Go | xml.NewDecoder(input) |
Disable entity resolution manually |
Dangerous Patterns
patterns:
# PHP - simplexml (XXE vulnerable by default)
- 'simplexml_load_(string|file)\s*\('
# PHP - DOMDocument with LIBXML_NOENT
- '(loadXML|->load)\s*\([^)]*LIBXML_NOENT'
# Python - lxml (resolve_entities=True by default)
- 'lxml\.etree\.(parse|fromstring)\s*\('
- 'etree\.XMLParser\s*\('
# Python - xml.sax (external entities enabled)
- 'xml\.sax\.parse(String)?\s*\('
# Java - DocumentBuilderFactory/SAXParserFactory/XMLReader (XXE by default)
- 'DocumentBuilderFactory\.newInstance\s*\('
- 'DocumentBuilder\s*\.\s*parse\s*\('
- 'SAXParserFactory\.newInstance\s*\('
- 'SAXParser\s*\.\s*parse\s*\('
- '(XMLReader\s*\.\s*parse|createXMLReader)\s*\('
# Go - encoding/xml
- 'xml\.(NewDecoder|Unmarshal)\s*\('
# Node.js - libxmljs (XXE enabled)
- 'libxmljs\.parseXml(String)?\s*\('
Safe Patterns
safe_patterns:
# PHP - Entity loader disabled (PHP 7.x, deprecated 8.0, removed 8.2)
- 'libxml_disable_entity_loader\s*\(\s*true'
- 'LIBXML_NONET'
# Python - defusedxml / ElementTree (safe by default)
- 'defusedxml\.'
- 'defused\..*parse'
- 'xml\.etree\.ElementTree'
- 'ET\.(parse|fromstring)'
# Java - Secure configuration
- 'setFeature\s*\([^)]*external-general-entities[^)]*false'
- 'setFeature\s*\([^)]*external-parameter-entities[^)]*false'
- 'setFeature\s*\([^)]*disallow-doctype-decl[^)]*true'
- 'setFeature\s*\([^)]*load-external-dtd[^)]*false'
# Go
- 'Strict\s*=\s*true'
- 'Entity\s*=\s*nil'
# Node.js - xml2js (safe by default)
- 'xml2js\.'
- 'parseString\s*\('
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 · 105 lines · 30 tokens per session scan A 1306aced88fe
xxe-attacker is an agent published in the GitHub repository morodomi/dev-crew (1 stars, last pushed 3d ago), licensed MIT. It adds 30 tokens to every session and 1,145 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.