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 skills add UnboundCompute/security-agent-skills --skill hunting-xxe-and-xml-parser-trustgit clone --depth 1 https://github.com/UnboundCompute/security-agent-skillsWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/unboundcompute/security-agent-skills/hunting-xxe-and-xml-parser-trust)<a href="https://agentmods.dev/skills/unboundcompute/security-agent-skills/hunting-xxe-and-xml-parser-trust"><img src="https://agentmods.dev/badge/skills/unboundcompute/security-agent-skills/hunting-xxe-and-xml-parser-trust/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/unboundcompute/security-agent-skills/hunting-xxe-and-xml-parser-trust"><img src="https://agentmods.dev/badge/skills/unboundcompute/security-agent-skills/hunting-xxe-and-xml-parser-trust.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What 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 5.1 | $0.00184 | $0.02011 |
| Opus 5.5 | $0.00074 | $0.00804 |
| Sonnet 5.5 | $0.00037 | $0.00402 |
| Haiku 4.5 | $0.00018 | $0.00201 |
Grade A, and why
hunting-xxe-and-xml-parser-trust 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 1mo ago.
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 — 138 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Hunting XXE and XML parser trust: when the parser fetches what the document asks for
An XML parser is dangerous when it honors the parts of the XML specification that let a document reach outside itself: a document type definition can declare external entities that the parser resolves by reading a local file or fetching a URL, parameter entities can drive that resolution even when the result is never reflected, and XInclude can pull in external content directly. Untrusted XML that reaches such a parser turns into local file disclosure, server-side request forgery including to internal and cloud-metadata endpoints, blind out-of-band exfiltration, and denial of service by recursive entity expansion. The XML is frequently not obvious: office documents, SVG images, SOAP envelopes, and federated identity assertions all carry XML into a parser. The one fact that governs everything is how the specific parser is configured. You find XXE by locating every XML parse of untrusted input and reading whether DTDs and external entities are enabled.
When to use
- A service parses XML from request bodies, file uploads, or federated messages.
- Uploads accept formats that contain XML, such as office documents or SVG images.
- A parser is constructed without an explicit secure configuration, or a default-insecure library is used.
Scope check
Test XXE only against services you own or are authorized to assess, on non-production infrastructure, because a confirmed case reads server files or reaches internal endpoints. Use inert markers and a destination you control for any out-of-band probe, and stay within the authorized scope. If you can't name the authorization, stop.
The loop
- Establish the parser configuration first. For each XML parse of untrusted input, read how the parser is constructed: whether DTD processing, external general entities, external parameter entities, and XInclude are enabled or disabled, on the exact library and version in use. This is the false-positive killer: a parser with secure processing on and external entities off is not vulnerable no matter what the document declares. Name the configuration before judging the document.
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.
- 1mo ago First seen · 138 lines · 184 tokens per session scan A af7f37983fa4
hunting-xxe-and-xml-parser-trust is a skill published in the GitHub repository UnboundCompute/security-agent-skills (5 stars, last pushed 1mo ago), licensed MIT. It adds 184 tokens to every session and 2,011 once invoked, about $0.0007 per session on Opus 5.5. 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 2026-09-05.
Other skills, from other repositories
integrate-arcjet-guard-cloudflare-think
Integrate Arcjet security into a Cloudflare Think app using @arcjet/guard — assign guardHooks().beforeToolCall on a Think subclass so the hook gates tools, and read a caller-owned id from helper options. Use when asked to add Arcjet to Cloudflare Think, @cloudflare/think, rate limit its tools, screen inbound messages…
protect
Add Arcjet request protection to JavaScript and TypeScript HTTP handlers. Use when protecting Next.js, Express, Fastify, SvelteKit, Remix, React Router, Hono, Astro, Nuxt, Bun, Deno, NestJS, or Node.js routes with rate limiting, bot detection, Shield, email validation, or sensitive info detection.
create-auth-skill
Scaffold and implement authentication in TypeScript/JavaScript apps using Better Auth. Detect frameworks, configure database adapters, set up route handlers, add OAuth providers, and create auth UI pages. Use when users want to add login, sign-up, or authentication to a new or existing project with Better Auth.
fhir-developer-skill
FHIR API development guide for building healthcare endpoints. Use when: (1) Creating FHIR REST endpoints (Patient, Observation, Encounter, Condition, MedicationRequest), (2) Validating FHIR resources and returning proper HTTP status codes and error responses, (3) Implementing SMART on FHIR authorization and OAuth…
api-security
Reviews REST and GraphQL APIs against the OWASP API Security Top 10:2023. Auto-invoked when reviewing OpenAPI/Swagger specs, API endpoint code, or GraphQL schemas. Covers BOLA, BFLA, authentication, rate limiting, and SSRF. Produces findings mapped to API1-API10 with remediation guidance.
create-auth-skill
Scaffold and implement authentication in TypeScript/JavaScript apps using Better Auth. Detect frameworks, configure database adapters, set up route handlers, add OAuth providers, and create auth UI pages. Use when users want to add login, sign-up, or authentication to a new or existing project with Better Auth.