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 cxcscmu/SkillLearnBench --skill druid-javascript-rcegit clone --depth 1 https://github.com/cxcscmu/SkillLearnBenchWrote 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/cxcscmu/skilllearnbench/druid-javascript-rce)<a href="https://agentmods.dev/skills/cxcscmu/skilllearnbench/druid-javascript-rce"><img src="https://agentmods.dev/badge/skills/cxcscmu/skilllearnbench/druid-javascript-rce.svg" alt="Measured on agentmods" 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 | $0.00036 | $0.00460 |
| Opus 5 | $0.00018 | $0.00230 |
| Sonnet 5 | $0.00007 | $0.00092 |
| Haiku 4.5 | $0.00004 | $0.00046 |
Grade A, and why
druid-javascript-rce 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 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.
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.
What it actually says
Apache Druid JavaScript RCE Vulnerability
Overview
Apache Druid 0.20.0 allows authenticated users to execute arbitrary server-side code through JavaScript-based features (filters, aggregators, extraction functions, etc.) even when JavaScript is disabled via druid.javascript.enabled=false.
Root Cause
All JavaScript-related classes use @JacksonInject JavaScriptConfig config to receive the server-side JavaScript configuration. Jackson's default behavior allows JSON input to override injected values via an empty key "".
Affected Classes
JavaScriptDimFilter- processing moduleJavaScriptAggregatorFactory- processing moduleJavaScriptExtractionFn- processing moduleJavaScriptPostAggregator- processing moduleJavaScriptParseSpec- core moduleJavaScriptTieredBrokerSelectorStrategy- server module (already has constructor check)
Fix Strategy
For each affected class:
- Change
@JacksonInjectto@JacksonInject(useInput = OptBoolean.FALSE) - Add
Preconditions.checkState(config.isEnabled(), "JavaScript is disabled")in constructors that don't already have it
Exploit Payload Example
{
"type": "index",
"spec": {
"dataSchema": {
"transformSpec": {
"filter": {
"type": "javascript",
"dimension": "dim",
"function": "function(x){java.lang.Runtime.getRuntime().exec('cmd')}",
"": {"enabled": true}
}
}
}
}
}
Modules Requiring Rebuild
druid-core(JavaScriptParseSpec)druid-processing(JavaScriptDimFilter, JavaScriptAggregatorFactory, JavaScriptExtractionFn, JavaScriptPostAggregator)druid-server(JavaScriptTieredBrokerSelectorStrategy)druid-indexing-service(sampler endpoint, depends on above)
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.
- 3d ago First seen · 57 lines · 36 tokens per session scan A c218c08f4ea7
druid-javascript-rce is a skill published in the GitHub repository cxcscmu/SkillLearnBench (83 stars, last pushed 1mo ago), licensed MIT. It adds 36 tokens to every session and 460 once invoked, about $0.0002 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 2026-09-03.
Other skills, from other repositories
agentsop-dify
SOP for building LLM applications on Dify — visual workflow + chatflow + agent + RAG knowledge base + plugin marketplace + observability, self-hostable. Use when shipping LLM apps fast with a "no-code to pro-code" gradient, especially when non-engineers need to co-author the flow.
agentsop-dspy
Operating SOP for DSPy (Stanford NLP) — the declarative framework for "programming, not prompting" language models. Activate when the user says any of: "use DSPy", "compile a prompt", "optimize prompts/programs", "MIPRO/MIPROv2", "BootstrapFewShot", "GEPA", "Signatures + Modules", "teleprompter", "auto-tune prompts…
agentsop-output-format-by-model
Pick an LM output format per (task x consumer x model) rather than by reflex: different formats carry different cognitive load (e.g. code-in-JSON makes the same model write worse code than plain-text+diff, while asking for prose when you need a typed object fails the other way). Use when designing or debugging an LM's…
senior-data-engineer
World-class data engineering skill for building scalable data pipelines, ETL/ELT systems, real-time streaming, and data infrastructure. Expertise in Python, SQL, Spark, Airflow, dbt, Kafka, Flink, Kinesis, and modern data stack. Includes data modeling, pipeline orchestration, data quality, streaming quality…
agentsop-crewai
SOP for building multi-agent systems with CrewAI — role-based collaboration, sequential/hierarchical processes, Flows, memory, delegation. Use when modeling agent teams with clear roles and task pipelines.
agentsop-framework-selection
Neutral, framework-agnostic decision tree for project kickoff: "which agent / RAG / LLM framework should I reach for?" Synthesizes the ecosystem sections of 7 landmark-project SOPs (LangGraph, LlamaIndex, DSPy, CrewAI, vLLM, Aider, Dify) into one layered rubric. Core stance: frameworks are LAYERS, not competitors — a…