CategoryWeightCategory scoreContribution

Securityprompt, exec, net, exfil, eval

35%

30.8 pts

Supply chainhash, typosquat, maintainer, lockfile

20%

100

20.0 pts

Maintenancestaleness, pinning, CI

15%

100

15.0 pts

TransparencySKILL.md, perms, README

15%

100

15.0 pts

Communityinstalls, verify, response

15%

100

15.0 pts

Findings & checks · 1 flagged

Securityscore 88 · 1 finding

MEDIUMInstruction telling the agent not to ask for approvalSS-SKILL-INJECT-DONT-ASK-01 · Prompt injection · AGENTS.md

MEDIUM — it fires on intent; the real damage depends on the host agent's own approval-gating.

Why it matters

The text {match} tells the agent to skip the normal "ask the user first" gate. Used adversarially it removes the human-in-the-loop check before destructive or sensitive actions, turning a normally-gated agent into a fire-and-forget executor.

The exact value spotted

excerptAGENTS.md· markdown

364- Use `from_env()` patterns — never hardcode credentials

365- Never print credential values in conversation output

366- **Do not prompt the user to set env vars** unless skill execution actually fails due to a

… (108 chars elided on L366)

367- Any skill that writes via MCP must show the query + estimated impact and require explicit

… (100 chars elided on L367)

368- Use `disable-model-invocation: true` for write/deploy skills to prevent auto-triggering

Occurrences

1 occurrence · at L366

How to fix

Remove the approval-skipping instruction, or scope it narrowly to a specific safe, reversible action.

Delete blanket "don't ask / no need to confirm" directives from the skill.
If the skill is a genuine autonomous job, restrict the opt-out to a named non-destructive action rather than all actions.

Framework references

OWASPLLM01 ATLASAML.T0051

Trace & refs

ruleSS-SKILL-INJECT-DONT-ASK-01sha2568169c469ab5917e7…rubric 365aacaView on GitHub

Supply chainscore 100 · 0 findings

✓—All supply chain checks passedNo findings in this category for the latest scan.pass

Maintenancescore 100 · 0 findings

✓—All maintenance checks passedNo findings in this category for the latest scan.pass

Transparencyscore 100 · 0 findings

✓—All transparency checks passedNo findings in this category for the latest scan.pass

Communityscore 100 · 0 findings

✓—All community checks passedNo findings in this category for the latest scan.pass

The primary manifest — the file an agent reads to learn what this artifact does.

README.md · 1 file

README.md7.0 KB · Markdown

Neo4j Agent Skills

Agent skills for Neo4j — Cypher queries, graph modeling, drivers, imports, GraphRAG, GDS, vector indexes, and Aura provisioning.

Browse and install at [skills.sh/neo4j-contrib/neo4j-skills](https://skills.sh/neo4j-contrib/neo4j-skills).

npx skills add https://github.com/neo4j-contrib/neo4j-skills

Configuration

Set these before or during installation:

Variable	Description
`NEO4J_URI`	`neo4j+s://<dbid>.databases.neo4j.io` (Aura) or `neo4j://localhost:7687` (local)
`NEO4J_USERNAME`	Database username (default: `neo4j`)
`NEO4J_PASSWORD`	Database password
`NEO4J_DATABASE`	Target database (default: `neo4j`)

Installation

Gemini CLI

gemini extensions install https://github.com/neo4j-contrib/neo4j-skills

Enter your env vars when prompted. Then run gemini and use /extensions list to verify.

Antigravity CLI

If you are migrating from Gemini CLI, import existing Gemini extensions automatically:

agy plugin import gemini

This auto-converts the gemini-extension.json manifest and copies skills into .agents/skills/. Then run agy and use /plugins list to verify.

Claude Code

/plugin marketplace add https://github.com/neo4j-contrib/neo4j-skills.git
/plugin install neo4j-skills@neo4j-skills-marketplace

Use /plugin list to verify, or /reload-plugins after installation.

Codex

git clone https://github.com/neo4j-contrib/neo4j-skills.git
mkdir -p ~/.codex/plugins
cp -R neo4j-skills ~/.codex/plugins/neo4j-skills

Add to ~/.agents/plugins/marketplace.json:

{
  "name": "neo4j-marketplace",
  "interface": { "displayName": "Neo4j Skills" },
  "plugins": [
    {
      "name": "neo4j-skills",
      "source": { "source": "local", "path": "./plugins/neo4j-skills" },
      "policy": { "installation": "AVAILABLE" },
      "category": "Database"
    }
  ]
}

Available Skills

Querying & Modeling

Skill	Description
`neo4j-cypher-skill`	Write, optimize, and debug Cypher queries. Covers CYPHER 25 syntax, query planning, indexes, and common patterns.
`neo4j-modeling-skill`	Design and review graph data models. Covers node/relationship patterns, property choices, and relational-to-graph migration.
`neo4j-getting-started-skill`	Zero-to-app walkthrough: provision → model → load → query. Use for first-time setup on Aura or Docker.

Importing Data

Skill	Description
`neo4j-import-skill`	Load structured data (CSV, JSON) via `LOAD CSV`, `neo4j-admin import`, and the Data Importer GUI.
`neo4j-document-import-skill`	Extract knowledge graphs from unstructured documents and PDFs using `SimpleKGPipeline`.
`neo4j-migration-skill`	Upgrade drivers and Cypher from 4.x/5.x to 2025.x. Covers API changes, deprecated functions, and Cypher 25 syntax.

AI & Search

Skill	Description
`neo4j-vector-index-skill`	Create and query vector indexes for semantic similarity search. Covers index creation, embedding ingestion, and `ai.text.embed()` [2025.12].
`neo4j-genai-plugin-skill`	In-Cypher LLM integration via `ai.text.*` functions [2025.12]: embeddings, text completion, structured output, chat, tokenization, and pure-Cypher GraphRAG.
`neo4j-graphrag-skill`	Build GraphRAG retrieval pipelines with `neo4j-graphrag`. Covers retriever selection (`VectorCypherRetriever`, `HybridCypherRetriever`), `retrieval_query` patterns, and LangChain/LlamaIndex integration.
`neo4j-agent-memory-skill`	Graph-native agent memory: short-term (conversations), long-term (POLE+O entity model), and reasoning traces. Covers `neo4j-agent-memory`, NAMS, MCP, LangChain, CrewAI, ADK.
`neo4j-mcp-skill`	Set up and use the Neo4j MCP server for tool-based agent access to the database.

Graph Data Science

Skill	Description
`neo4j-gds-skill`	Run GDS algorithms with the embedded GDS plugin on Aura Pro, self-managed, local, or offline Neo4j.
`neo4j-aura-graph-analytics-skill`	Run serverless Aura Graph Analytics sessions via Python client or AuraDB Cypher API projection/session management.
`neo4j-snowflake-graph-analytics-skill`	Run Neo4j Graph Analytics algorithms (PageRank, Louvain, WCC, Dijkstra, KNN, Node2Vec) directly inside Snowflake without moving data.

Drivers

Skill	Description
`neo4j-driver-python-skill`	Python driver: `execute_query`, sessions, transactions, async, UNWIND batching, data types.
`neo4j-driver-javascript-skill`	JavaScript/TypeScript driver v6: `executeQuery`, managed transactions, RxJS, data types.
`neo4j-driver-java-skill`	Java driver: `ExecutableQuery`, managed/explicit transactions, object mapping, reactive.
`neo4j-driver-dotnet-skill`	.NET/C# driver: `ExecuteReadAsync`/`ExecuteWriteAsync`, DI registration, `IResultCursor`.
`neo4j-driver-go-skill`	Go driver v6: `ExecuteQuery`, generic helpers, spatial types, connection configuration.

Frameworks & Platforms

Skill	Description
`neo4j-graphql-skill`	Build GraphQL APIs backed by Neo4j using `@neo4j/graphql`. Covers type definitions, `@relationship`, `@cypher`, and filtering.
`neo4j-spring-data-skill`	Spring Boot + Neo4j with Spring Data Neo4j: `@Node`, `@Relationship`, repositories, projections.
`neo4j-cli-tools-skill`	DB admin via `neo4j-admin`, `cypher-shell`, `aura-cli`, and `neo4j-cli` (preview unified CLI). Covers backups, imports, user management, Aura provisioning, and agent skill install.
`neo4j-aura-provisioning-skill`	Create and manage Neo4j Aura instances via the Aura CLI and REST API. Covers async polling, credential handling, and tier selection.
`neo4j-aura-agent-skill`	Create, configure, and invoke Aura Agents via the v2beta1 REST API. Covers CypherTemplate, SimilaritySearch, and Text2Cypher tools, system prompts, REST/MCP deployment, and OAuth2 auth.

What are Agent Skills?

Agent Skills are a standardized format for domain-specific AI agent knowledge. Each skill bundles step-by-step instructions, on-demand reference docs, and executable scripts — loaded progressively to keep context lean. See agentskills.io/specification.

Contributing

Pull requests welcome — new skills or improvements to existing ones.

License

MIT — see the LICENSE file for details.

Neo4J Skills— plugin

Is Neo4J Skills safe to install?

Neo4j Agent Skills

Configuration

Installation

Gemini CLI

Antigravity CLI

Claude Code

Codex

Available Skills

Querying & Modeling

Importing Data

AI & Search

Graph Data Science

Drivers

Frameworks & Platforms

What are Agent Skills?

Contributing

License

Audit the pieces. Scan the whole. Decide.