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-xpath-and-xml-query-injectiongit 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-xpath-and-xml-query-injection)<a href="https://agentmods.dev/skills/unboundcompute/security-agent-skills/hunting-xpath-and-xml-query-injection"><img src="https://agentmods.dev/badge/skills/unboundcompute/security-agent-skills/hunting-xpath-and-xml-query-injection/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-xpath-and-xml-query-injection"><img src="https://agentmods.dev/badge/skills/unboundcompute/security-agent-skills/hunting-xpath-and-xml-query-injection.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 | $0.00160 | $0.01999 |
| Opus 5.5 | $0.00064 | $0.00800 |
| Sonnet 5.5 | $0.00032 | $0.00400 |
| Haiku 4.5 | $0.00016 | $0.00200 |
Grade A, and why
hunting-xpath-and-xml-query-injection 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 — 137 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Hunting XPath and XQuery injection: when input rewrites the query
XPath and XQuery are to XML what SQL is to a relational database, and they carry the same injection flaw. When an application builds a query by pasting untrusted input into the expression string, an attacker who supplies query syntax instead of a plain value changes what the query means. A login check that looks up a user node by matching a name and password predicate can be turned into a predicate that is always true, logging in as the first user with no credential. A lookup scoped to one node can be widened to walk the entire document and return records the caller should never see. Because XML documents have no table grants, the whole document is usually reachable once the expression is under attacker control. You find these by locating every expression built from request data and asking whether the input is bound as a parameter or concatenated as syntax.
When to use
- Code builds an XPath or XQuery expression by concatenating or interpolating request-derived strings.
- Authentication, authorization, or lookup logic evaluates such an expression against an XML document.
- An XML database or an XML-backed configuration store is queried with input-derived expressions.
Scope check
Test XPath and XQuery injection only against applications you own or are authorized to assess, with test accounts and test data, because a confirming query can read other users' records out of the document. Prefer boolean and structural probes over bulk extraction, and coordinate before dumping data. If you can't name the authorization, stop.
The loop
- Establish that the expression is concatenated, not parameterized, first. Locate every XPath or XQuery evaluation and read how its expression string is assembled. This is the false-positive killer: if the expression is a fixed literal and untrusted input is bound through a variable resolver or a precompiled expression with typed parameters, the input can only be a value and the query structure is fixed, so there is no injection. Name the evaluations where input is pasted into the string.
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 · 137 lines · 160 tokens per session scan A d9630c251084
hunting-xpath-and-xml-query-injection is a skill published in the GitHub repository UnboundCompute/security-agent-skills (5 stars, last pushed 1mo ago), licensed MIT. It adds 160 tokens to every session and 1,999 once invoked, about $0.0006 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
prodcheck-review
Review this codebase against the prodcheck pre-production checklists — security, performance, scale, integrations, post-launch readiness and people. Use when asked to check whether a project is ready to ship, to audit an area before launch, or to work through a specific checklist. Produces evidence with file:line…
integrate-arcjet-guard-genkit
Integrate Arcjet security into a Genkit JS agent using @arcjet/guard — wrap ai.defineTool, put guardMiddleware on generate({ use }) for unwrapped / MCP / filesystem tools, and read a caller-owned id from generate({ context }). Use when asked to add Arcjet to genkit, rate limit its tools, screen inbound messages, or…
integrate-arcjet-guard-tanstack-ai
Integrate Arcjet security into a TanStack AI chat() app using @arcjet/guard — put guardMiddleware first on chat({ middleware }) so onBeforeToolCall gates tools, and read a caller-owned id from chat({ context }). Use when asked to add Arcjet to TanStack AI, rate limit its tools, screen inbound messages, or block prompt…
integrate-arcjet-guard-claude-managed-agents
Integrate Arcjet security into Claude Managed Agents (hosted REST+SSE, beta managed-agents-2026-04-01) using @arcjet/guard — screen user.message / initialevents before sessions.events.send, and gate custom tools on agent.customtooluse. Use when asked to add Arcjet to Claude Managed Agents, rate limit custom tools, or…
linear-claude-skill
Manage Linear issues, projects, and teams.
varlock-claude-skill
Secure environment variable management ensuring secrets are never exposed in Claude sessions, terminals, logs, or git commits.