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-server-side-template-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-server-side-template-injection)<a href="https://agentmods.dev/skills/unboundcompute/security-agent-skills/hunting-server-side-template-injection"><img src="https://agentmods.dev/badge/skills/unboundcompute/security-agent-skills/hunting-server-side-template-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-server-side-template-injection"><img src="https://agentmods.dev/badge/skills/unboundcompute/security-agent-skills/hunting-server-side-template-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 | $0.00172 | $0.01973 |
| Opus 5.5 | $0.00069 | $0.00789 |
| Sonnet 5.5 | $0.00034 | $0.00395 |
| Haiku 4.5 | $0.00017 | $0.00197 |
Grade A, and why
hunting-server-side-template-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 server-side template injection: when input becomes the template, not the data
Template engines are safe when untrusted input is passed as a bound variable into a fixed, precompiled template: the value can only ever be data. Server-side template injection happens when input instead becomes part of the template that the engine compiles, either concatenated into a template string, supplied as the template name or path, or authored directly by a user in a feature that renders their markup. Now the engine evaluates the attacker's template expressions. The floor is expression evaluation and data disclosure; the ceiling, on many engines, is remote code execution by walking object attributes to reach a runtime, a loader, or a process API, and by escaping whatever sandbox the engine offers. The distinction that governs everything is whether input reaches compilation or only reaches rendering as data.
When to use
- Code builds a template by concatenating or interpolating untrusted input before handing it to the engine.
- A template name, path, or layout is selected from user input.
- A feature lets users author templates or expressions: email or report templates, themes, or rules.
Scope check
Test template injection only against applications you own or are authorized to assess, on non-production infrastructure, because a confirmed case often reaches code execution. Prove the class with an inert arithmetic or string expression before attempting anything further, and stay within the authorized instance. If you can't name the authorization, stop.
The loop
- Establish that input reaches compilation first. Determine whether the untrusted value is compiled as part of a template (a dynamic template string, a user-chosen template name, or user-authored markup) or is only bound as a variable into a fixed template. This is the false-positive killer: a value passed as data into a precompiled template is not template injection no matter how it renders. Confirm the value reaches the engine's compile or eval step before proceeding.
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 · 172 tokens per session scan A 49be960772a5
hunting-server-side-template-injection is a skill published in the GitHub repository UnboundCompute/security-agent-skills (5 stars, last pushed 1mo ago), licensed MIT. It adds 172 tokens to every session and 1,973 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.