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 clickjackinggit 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/clickjacking)<a href="https://agentmods.dev/skills/shulkwisec/bb-huge/clickjacking"><img src="https://agentmods.dev/badge/skills/shulkwisec/bb-huge/clickjacking/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/clickjacking"><img src="https://agentmods.dev/badge/skills/shulkwisec/bb-huge/clickjacking.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 | $0.00047 | $0.01253 |
| Opus 5 | $0.00023 | $0.00626 |
| Sonnet 5 | $0.00009 | $0.00251 |
| Haiku 4.5 | $0.00005 | $0.00125 |
Grade A, and why
clickjacking 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 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.
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.
This is a copy
100% identical to clickjacking — 0 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
How it starts
The opening of the file, as written. The whole thing — 164 lines — stays where its author put it; the contents beside it link to each section on GitHub.
SKILL: Clickjacking — Expert Attack Playbook
AI LOAD INSTRUCTION: Clickjacking (UI redress) techniques. Covers iframe transparency tricks, X-Frame-Options bypass, CSP frame-ancestors, multi-step clickjacking, drag-and-drop attacks, and chaining with other vulnerabilities. Often a "low severity" finding that becomes critical when targeting admin actions.
1. CORE CONCEPT
Clickjacking loads a target page in a transparent iframe overlaid on an attacker's page. The victim sees the attacker's UI but clicks on the invisible target page, performing unintended actions.
<style>
iframe { position: absolute; top: 0; left: 0; width: 100%; height: 100%; opacity: 0.0001; z-index: 2; }
.decoy { position: absolute; top: 200px; left: 100px; z-index: 1; }
</style>
<div class="decoy"><button>Click to win a prize!</button></div>
<iframe src="https://target.com/account/delete?confirm=yes"></iframe>
2. DETECTION — IS THE PAGE FRAMEABLE?
Check X-Frame-Options Header
X-Frame-Options: DENY → cannot be framed (secure)
X-Frame-Options: SAMEORIGIN → only same-origin framing (secure for cross-origin)
X-Frame-Options: ALLOW-FROM uri → deprecated, browser support inconsistent
(header absent) → frameable! (vulnerable)
Check CSP frame-ancestors
Content-Security-Policy: frame-ancestors 'none' → cannot be framed
Content-Security-Policy: frame-ancestors 'self' → same-origin only
Content-Security-Policy: frame-ancestors https://a.com → specific origin
(directive absent) → frameable
CSP frame-ancestors supersedes X-Frame-Options in modern browsers.
Quick PoC Test
<iframe src="https://target.com/sensitive-action" width="800" height="600"></iframe>
If the page loads in the iframe → frameable → potentially vulnerable.
JavaScript Frame Detection (from target page source)
// Common frame-busting code found in target pages:
if (top.location.hostname !== self.location.hostname) {
top.location.href = self.location.href;
}
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 · 164 lines · 47 tokens per session scan A e8d576fea77e
clickjacking is a skill published in the GitHub repository ShulkwiSEC/bb-huge (22 stars, last pushed 2mo ago), licensed MIT. It adds 47 tokens to every session and 1,253 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 0 findings. It is 100% identical to clickjacking, differing in 0 lines, and is treated as a copy.
Other skills, from other repositories
playwright-uitest
Generate Playwright UI tests and visual smoke reports for delivery POC frontends.
XSS_SKILL
Cross-site scripting skill vision validation.
browser-test
Browser testing using Chrome DevTools MCP and Playwright for visual verification. Start dev server, navigate, screenshot, Lighthouse audit, console errors, network check. Use when: (1) verifying frontend changes, (2) accessibility auditing, (3) performance testing, (4) visual regression. Triggers: /browser-test, 'test…
core
Core agent-browser usage guide. Read this before running any agent-browser commands. Covers the snapshot-and-ref workflow, navigating pages, interacting with elements (click, fill, type, select), extracting text and data, taking screenshots, managing tabs, handling forms and auth, waiting for content, running multiple…
browser-automation
Browser automation security policy: trust zones (localhost GREEN / staging YELLOW / production RED), the agent-browser tool workflow, allowed vs prohibited actions, and config/secret file handling. Use when the task involves browser automation, agent-browser, Playwright or Chrome DevTools MCP, taking screenshots of…
browser
Web browser automation with AI-optimized snapshots for claude-flow agents.