java-javascript-security

java-javascript-security is a skill for Claude Code, Codex from cxcscmu/SkillLearnBench. It costs 25 tokens per session (335 once invoked), scanned B, original, MIT.

Security guidance for running JavaScript inside Java applications through script engines such as Rhino or Nashorn. It explains how scripts might reach Java classes and run system commands.

In plain words
What is it for?
Use it to review JavaScript engine settings, restrict accessible Java classes, sandbox scripts, and validate input data.
Why use it?
It helps prevent untrusted scripts from gaining access to Java or the operating system. It also covers when to disable scripting and how to limit access when scripting is required.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

Good fit Use it to review JavaScript engine settings, restrict accessible Java classes, sandbox scripts, and validate input data.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/cxcscmu/skilllearnbench/java-javascript-security
Install

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.

Any agent
npx skills add cxcscmu/SkillLearnBench --skill java-javascript-security
Clone the repo
git clone --depth 1 https://github.com/cxcscmu/SkillLearnBench

Made for: Claude Code, Codex.

Wrote 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.

agentmods badge for java-javascript-security

README.md
[![agentmods](https://agentmods.dev/badge/skills/cxcscmu/skilllearnbench/java-javascript-security.svg)](https://agentmods.dev/skills/cxcscmu/skilllearnbench/java-javascript-security)
Your own site
<a href="https://agentmods.dev/skills/cxcscmu/skilllearnbench/java-javascript-security"><img src="https://agentmods.dev/badge/skills/cxcscmu/skilllearnbench/java-javascript-security.svg" alt="Measured on agentmods" height="20"></a>
Per session 25 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 335 The whole file, excluding the scripts and references it only reads on demand.
Security scan B 1 finding. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00025 $0.00335
Opus 5 $0.00013 $0.00168
Sonnet 5 $0.00005 $0.00067
Haiku 4.5 $0.00003 $0.00034

Measured 3d ago against content hash 13c222bb708e, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade B, and why

java-javascript-security scanned grade B 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 3d 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.

Recursive force deletemediumDestructive command

rm -rf with a variable or a broad path is one typo away from removing the wrong tree.

Runtime.getRuntime().exec("rm -rf /");

Downgraded: this mod is about security review, or the phrase is quoted, so it is likely naming the pattern rather than instructing it.

skills/b1-one-shot-gemini-3-flash-preview/fix-security-bug/java-javascript-security/SKILL.md · 49 lines

What it actually says

Java JavaScript Security

When executing JavaScript in a Java application, it is crucial to restrict the capabilities of the script to prevent Arbitrary Code Execution (ACE).

Vulnerability: Access to Java Classes

By default, many JavaScript engines (like Rhino, which Druid uses) allow the script to access Java classes.

var Runtime = java.lang.Runtime;
Runtime.getRuntime().exec("rm -rf /");

Mitigation: Disabling JavaScript if not needed

The best defense is to disable JavaScript execution entirely if it is not required. Apache Druid provides a configuration druid.javascript.enabled to control this.

Mitigation: Sandboxing

If JavaScript must be used, it should be sandboxed.

Rhino Sandboxing

In Rhino, you can use a ClassShutter to restrict which Java classes the script can access.

Context cx = Context.enter();
try {
    cx.setClassShutter(new ClassShutter() {
        @Override
        public boolean visibleToScripts(String fullClassName) {
            return fullClassName.startsWith("org.mycompany.safe.");
        }
    });
    // ...
} finally {
    Context.exit();
}

Mitigation: Input Validation

Always validate the JSON structure and ensure that security-critical configurations (like whether JS is enabled) cannot be overridden by user input. In Druid, this often involves ensuring @JacksonInject values are not overridable by JSON properties.

Changes

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.

  1. 3d ago First seen · 49 lines · 25 tokens per session scan B 13c222bb708e

Subscribe to this mod's changes

java-javascript-security is a skill published in the GitHub repository cxcscmu/SkillLearnBench (83 stars, last pushed 1mo ago), licensed MIT. It adds 25 tokens to every session and 335 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it B with 1 finding (recursive force delete). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-03.

Related

Other skills, from other repositories

ceo-setup

One-time onboarding for the executive/manager commitment workflow — delegation-heavy, meeting prep, decision capture, morning and evening digests. Creates a commitments project and installs two dashboard widgets. After successful setup this skill is excluded from selection until the marker file is deleted.

suyoumo/ClawProBench · 60 tokens

content-creator-setup

One-time onboarding for the content creator workflow — content pipeline stages, trend expiration, cross-platform cascades, heavy idea parking. After successful setup this skill is excluded from selection until the marker file is deleted.

suyoumo/ClawProBench · 47 tokens

github

GitHub API integration via HTTP tool with automatic credential injection.

suyoumo/ClawProBench · 13 tokens

idea-parking

Park interesting ideas for later consideration, resurface them periodically, and promote to commitments when ready.

suyoumo/ClawProBench · 23 tokens

agentsop-llm-artifact-versioning

Enhancement overlay — version the WHOLE deployable LLM-app artifact as one bundle: prompts + compiled programs + model snapshot pins + retrieval config + eval-set version, versioned together so a deploy is reproducible and rollback is atomic. Activate when preparing to deploy an LLM app, when asking "what exactly is…

agentsope/SkillAlchemy · 223 tokens

agentsop-llamaindex

Operating-system distillation of LlamaIndex — the leading RAG / document-agent framework. Activate when the calling agent must build, debug, harden, or evaluate a Retrieval-Augmented Generation pipeline over unstructured/private data, decide between RAG primitives (Index types, retrievers, query engines, routers…

agentsope/SkillAlchemy · 178 tokens