sc-ssti

sc-ssti is a skill for Claude Code, Codex from ersinkoc/security-check. It costs 15 tokens per session (1,467 once invoked), scanned A, original, MIT.

A security check for server-side template injection. Templates are files or strings used to generate pages; this attack occurs when untrusted input becomes template code instead of ordinary text.

In plain words
What is it for?
Reviewing template compilation and rendering across engines such as Jinja2, Twig, Freemarker, Pug, Handlebars, ERB, Mako, Thymeleaf, and Go templates.
Why use it?
It helps find cases where an attacker could make the server run unintended template commands or arbitrary code.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

Good fit Reviewing template compilation and rendering across engines such as Jinja2, Twig, Freemarker, Pug, Handlebars, ERB, Mako, Thymeleaf, and Go templates.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/ersinkoc/security-check/sc-ssti
Install

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.

Any agent
npx skills add ersinkoc/security-check --skill sc-ssti
Clone the repo
git clone --depth 1 https://github.com/ersinkoc/security-check

Made for: Claude Code, Codex.

Wrote 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.

agentmods badge for sc-ssti

README.md
[![agentmods](https://agentmods.dev/badge/skills/ersinkoc/security-check/sc-ssti/github.svg)](https://agentmods.dev/skills/ersinkoc/security-check/sc-ssti)
Your own site
<a href="https://agentmods.dev/skills/ersinkoc/security-check/sc-ssti"><img src="https://agentmods.dev/badge/skills/ersinkoc/security-check/sc-ssti/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.

agentmods 80×15 button for sc-ssti

Your own site · 80×15
<a href="https://agentmods.dev/skills/ersinkoc/security-check/sc-ssti"><img src="https://agentmods.dev/badge/skills/ersinkoc/security-check/sc-ssti.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 15 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,467 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 1 finding. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00015 $0.01467
Opus 5 $0.00008 $0.00733
Sonnet 5 $0.00003 $0.00293
Haiku 4.5 $0.00002 $0.00147

Measured 9d ago against content hash 3c7ae77be6b5, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

sc-ssti scanned grade A with 1 finding 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 9d 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.

Unrestricted tool accesslowExcessive agency

A wildcard tool grant or "run any command" leaves no least-privilege boundary at all.

Detects server-side template injection vulnerabilities where user input is embedded into template strings before compilation/rendering, allowing attackers to execute arbitrary code on the server. Covers Jinja2, Twig, Fre

Downgraded: this mod is about security review, or the phrase is quoted, so it is likely naming the pattern rather than instructing it.

skills/sc-ssti/SKILL.md · 144 lines

How it starts

The opening of the file, as written. The whole thing — 144 lines — stays where its author put it; the contents beside it link to each section on GitHub.

SC: Server-Side Template Injection (SSTI)

Purpose

Detects server-side template injection vulnerabilities where user input is embedded into template strings before compilation/rendering, allowing attackers to execute arbitrary code on the server. Covers Jinja2, Twig, Freemarker, Velocity, Pug, Handlebars, ERB, Mako, Thymeleaf, and Go templates.

Activation

Called by sc-orchestrator during Phase 2 when template engines are detected.

Phase 1: Discovery

File Patterns to Search

**/*.py, **/*.php, **/*.java, **/*.rb, **/*.js, **/*.ts, **/*.go,
**/templates/*, **/views/*, **/*template*, **/*render*, **/*view*

Keyword Patterns to Search

# Python/Jinja2
"render_template_string(", "Template(", "Environment(",
"from_string(", "jinja2.Template("

# PHP/Twig
"$twig->createTemplate(", "Twig\\Template", "renderString("

# Java/Freemarker/Velocity/Thymeleaf
"new Template(", "freemarker", "VelocityEngine",
"templateEngine.process(", "StandardDialect"

# Ruby/ERB
"ERB.new(", "render inline:", "Erubis"

# JavaScript/Pug/Handlebars/EJS
"pug.render(", "pug.compile(", "Handlebars.compile(",
"ejs.render(", "nunjucks.renderString("

# Go
"template.New(", "text/template", "html/template",
".Parse(", "template.Must("

Semantic Patterns

  1. User input passed as the template STRING (not as template DATA)
  2. String concatenation used to build template content before compilation
  3. Template created from user-controlled source (database, HTTP parameter)
  4. render_template_string() instead of render_template() in Flask

Phase 2: Verification

Key Distinction

The vulnerability occurs when user input becomes part of the TEMPLATE CODE, not the template DATA:

# SAFE: User input as template data (parameterized)
render_template('hello.html', name=user_input)

# VULNERABLE: User input as template code
render_template_string(f"Hello {user_input}")
# If user_input = "{{7*7}}", the template engine evaluates it as 49
# If user_input = "{{config.items()}}", it leaks Flask config

Read the full file on GitHub · 144 lines

Changes

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.

  1. 9d ago First seen · 144 lines · 15 tokens per session scan A 3c7ae77be6b5

Subscribe to this mod's changes

sc-ssti is a skill published in the GitHub repository ersinkoc/security-check (56 stars, last pushed 2mo ago), licensed MIT. It adds 15 tokens to every session and 1,467 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it A with 1 finding (unrestricted tool access). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

Related

Other skills, from other repositories

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

local-ai-agents

Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…

microsoft/ai-agents-for-beginners · 200 tokens

next-cache-components-adoption

Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…

vercel/next.js · 95 tokens

insight-error-page

Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…

vercel/next.js · 83 tokens

next-cache-components-optimizer

Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…

vercel/next.js · 170 tokens

next-partial-prefetching-adoption

Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…

vercel/next.js · 103 tokens