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 RadOrigin-LLC/RAD-Claude-Skills --skill chrome-ext-securitygit clone --depth 1 https://github.com/RadOrigin-LLC/RAD-Claude-SkillsWrote 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/radorigin-llc/rad-claude-skills/chrome-ext-security)<a href="https://agentmods.dev/skills/radorigin-llc/rad-claude-skills/chrome-ext-security"><img src="https://agentmods.dev/badge/skills/radorigin-llc/rad-claude-skills/chrome-ext-security/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/radorigin-llc/rad-claude-skills/chrome-ext-security"><img src="https://agentmods.dev/badge/skills/radorigin-llc/rad-claude-skills/chrome-ext-security.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 | $0.00110 | $0.00784 |
| Opus 5 | $0.00055 | $0.00392 |
| Sonnet 5 | $0.00022 | $0.00157 |
| Haiku 4.5 | $0.00011 | $0.00078 |
Grade A, and why
chrome-ext-security 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 10d 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.
How it starts
The opening of the file, as written. The whole thing — 82 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Chrome Extension Security
MV3 enforces a strict security model. All executable code must be bundled locally. The Content Security Policy bans eval() and remote scripts. Content scripts operate in an isolated world but share a DOM with potentially hostile pages. The service worker is the trusted core — all messages from content scripts must be validated.
Hard Security Rules
Remote Code Ban
All executable JavaScript must be bundled locally within the extension package. No fetching scripts from CDNs, no dynamically loaded SDKs. Violating this triggers Blue Argon CWS rejection.
eval() and String-to-Code Prohibition
These are banned in standard extension contexts:
eval()new Function(string)setTimeout(string)/setInterval(string)
Escape hatches for legitimate needs:
userScriptsAPI (Chrome 120+) for user script managers- Sandboxed iframes (no Chrome API access)
wasm-unsafe-evalin CSP for WebAssembly
Content Security Policy (MV3)
Declared as an object (not a string). No remote domains in script-src, worker-src, object-src, or style-src:
{
"content_security_policy": {
"extension_pages": "script-src 'self'; object-src 'self'",
"sandbox": "sandbox allow-scripts; script-src 'self' 'unsafe-eval'"
}
}
Code Obfuscation Ban
Standard minification (whitespace removal, variable shortening) is allowed. Base64 encoding logic, character encoding to hide functionality, or other obfuscation triggers Red Titanium rejection.
Trust Boundaries
Content Scripts Are Untrusted
Content scripts share an execution environment with potentially malicious web pages. The service worker must:
- Validate and sanitize ALL messages received from content scripts
- Never pass content script data to
eval(),innerHTML, or other injection sinks - Treat content script messages like untrusted user input at an API boundary
DOM Injection Safety
When injecting UI into web pages:
- Use
textContentorinnerTextinstead ofinnerHTMLfor text - Use
document.createElement()for DOM construction - Enforce Trusted Types API when handling HTML
- Mount injected UI inside Shadow DOM to isolate from host page
What ships with it
2 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 10d ago First seen · 82 lines · 110 tokens per session scan A 860bd7ce28a2
chrome-ext-security is a skill published in the GitHub repository RadOrigin-LLC/RAD-Claude-Skills (5 stars, last pushed 24d ago), licensed Apache-2.0. It adds 110 tokens to every session and 784 once invoked, about $0.0006 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
bug-reporting
Load this skill whenever you are filing, reviewing, or generating accessibility bug reports — whether from automated tool output, manual testing, user reports, or testing with disabled people. The purpose of this skill is to make accessibility findings easier to report accurately, connect them to real people and…
mermaid
Load this skill whenever the project uses Mermaid diagrams — flowcharts, sequence diagrams, class diagrams, Gantt charts, or any Mermaid-rendered visualization. Under no circumstances render a Mermaid diagram without an accessible title, description, and text-based alternative. Absolutely always add accTitle: and…
svg
Load this skill whenever the project contains SVG graphics — inline SVGs, external SVG files, SVG icons, SVG illustrations, or SVG-based data visualizations. Under no circumstances use SVG without proper accessible titles, descriptions, and ARIA roles where required. Absolutely always add and to meaningful SVGs and…
audio-video
Load this skill whenever the project contains audio or video content, media players, podcasts, video embeds, or any / elements. Under no circumstances publish audio or video without captions, transcripts, and audio descriptions where required. Absolutely always apply WCAG 1.2 criteria for time-based media.
charts-graphs
Load this skill whenever the project contains charts, graphs, data visualizations, infographics, or any visual representation of data (bar charts, line charts, pie charts, scatter plots, dashboards). Under no circumstances render a chart without a text alternative, data table, or summary. Prioritize conveying the same…
ci-cd
Load this skill when configuring or reviewing CI/CD pipelines, GitHub Actions workflows, or automated testing setups. Ensures accessibility regressions are caught before code reaches production by enforcing quality gates, structured reporting, and layered automated + manual testing across all pages and user…