neo4j-document-import-skill

Pass

Audited by Gen Agent Trust Hub on Apr 28, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill provides standard documentation and code templates for building knowledge graphs. The code uses well-known libraries such as LangChain and the official Neo4j GraphRAG package.
  • [INDIRECT_PROMPT_INJECTION]: The skill describes a pipeline that processes unstructured documents (PDF, HTML, text) to extract entities using an LLM, which represents a potential surface for indirect prompt injection attacks where malicious content in the documents could influence the extraction process.
  • Ingestion points: Document content is ingested through the document_text variable within the Python code snippets in SKILL.md.
  • Boundary markers: The examples do not demonstrate the use of boundary markers or specific instructions to ignore embedded commands within the ingested text.
  • Capability inventory: The skill utilizes database write capabilities via driver.execute_query and network data loading via apoc.load.json.
  • Sanitization: No input sanitization or validation steps are included in the provided code templates.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 28, 2026, 04:43 PM