Skip to main content
subagent CX Codex

ssti-hunter — Claude Code subagent: SSTI detection and exploitation

ssti-hunter — a subagent for finding and exploiting Server-Side Template Injection (SSTI) across Jinja2, Twig, Velocity, FreeMarker, ERB, and Handlebars. Maps sandbox blocklists, identifies engine type, and chains bypasses to RCE.

no license ★ 1,298 updated 2026-06-12

Install into Claude Code · Manually: put the files in place All methods and platforms ↓
.claude/agents/ssti-hunter.md
Open on GitHub

What ssti-hunter does

ssti-hunter targets Server-Side Template Injection vulnerabilities where user input flows into template engines. It handles the engines commonly found in PR automation, configuration systems, and customization interfaces. The subagent identifies engine type through polyglot probes, systematically maps which class attributes pass through sandbox filters, then hunts for gaps to reach arbitrary code execution.

Investigation starts by querying the writeup-search database for proven techniques rather than rediscovering 2019 exploits. All matrices and blocklists go to disk under evidence/<target>/ssti/. It distinguishes between parsing and rendering phases—Mergify's /configuration-simulator parses only, while /pulls/{n}/simulator renders and leaks values. The subagent works with CVE-2025-27516 (unsafe |attr('format') in Jinja ≤ 3.1.5), classical chains through __mro__ and __subclasses__, and filter evasion via hex encoding, bracket notation, and runtime string construction to bypass source-level regex filters.

What it helps with

  • determine the template engine from application responses
  • find class attributes not blocked by the sandbox
  • build RCE chains through overlooked dunder methods
  • bypass source-level filters on __class__ and __globals__
  • map and persist sandbox blocklists per vulnerable surface

Example prompts for the agent

  • Test this template form for SSTI and tell me which engine it runs
  • Find the RCE path through the configuration language on this service
  • Map the Jinja2 sandbox blocklist for this application

How to install ssti-hunter

Manually: put the files in place

.claude/agents/ssti-hunter.md

For all projects use ~/.claude/agents/. Claude delegates by the description field or an @-mention

Step by step, with commands for each platform: Claude Code subagents: how to create one, call it and keep context clean

Questions about ssti-hunter

How do I install ssti-hunter in Claude Code?

Copy .claude/agents/ssti-hunter.md to your project's .claude/agents/ directory. The subagent will be available as an agent in the IDE.

What does ssti-hunter do?

It specializes in finding and exploiting Server-Side Template Injection vulnerabilities. It detects the template engine, maps sandbox restrictions, and discovers RCE paths through dunder methods and encoding bypasses.

Which template engines does ssti-hunter support?

Jinja2, Twig, Velocity, FreeMarker, ERB, Handlebars, and Thymeleaf. It works on any surface where user input renders through a template—PR automation rules, comments, admin-customizable templates.

Similar subagents

All subagents for Security →

From the same set43

The whole set →
dast-devils-advocate dast-devils-advocate — a skill that catches inflated vulnerabilities in DAST reports. CX Codex +1 ★ 1,298repo stars dast-devils-advocate dast-devils-advocate — an adversarial subagent that questions DAST findings, reruns PoC commands, flags publicly accessible data, and lowers inflated severity ratings before you submit reports. CX Codex +1 ★ 1,298repo stars ssti-hunter ssti-hunter is a Claude Code skill that investigates server-side template injection (SSTI). It activates for user-controlled templates, rule engines, and rendered messages. CX Codex +1 ★ 1,298repo stars pentest-agents-hunting The pentest-agents-hunting rule structures security hunting around scope, practical impact, and attack chains. It helps an agent drop weak leads and investigate confirmed bugs more deeply. CX Codex +1 ★ 1,298repo stars pentest-agents-techniques The pentest-agents-techniques rule guides agents through checks for authorization flaws and data leaks in web apps. Use it when testing systems you’re authorized to assess. CX Codex +1 ★ 1,298repo stars hunt hunt — a prompt for systematic vulnerability detection on target hosts. Reads scope, detects tech stack, auto-selects vuln classes by likelihood, and runs targeted tests with concrete payloads and WAF bypass rules. CX Codex +1 ★ 1,298repo stars hunt Conducts targeted vulnerability hunting by validating scope, fingerprinting stacks, and dispatching exploit tests. CX Codex +1 ★ 1,298repo stars autopilot autopilot coordinates security testing for a target by checking scope and program rules before dispatching specialized subagents. Autonomous mode runs through its completion checks before reporting. CX Codex +1 ★ 1,298repo stars

Project sponsors

Companies that keep this analytics open