neo4j-import-skill
Pass
Audited by Gen Agent Trust Hub on Sep 15, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and process data from external CSV, JSON, and Parquet sources, which represents a potential attack surface for indirect prompt injection. \n
- Ingestion points: Local and remote CSV/JSON files, and API responses as defined in SKILL.md and references/driver-batch-write.md. \n
- Boundary markers: The skill explicitly instructs the agent to implement a 'Write execution gate', requiring it to present the query and estimated row count to the user and wait for confirmation before execution. \n
- Capability inventory: The agent uses write-cypher and Bash tools to perform data operations. \n
- Sanitization: Instructions include type coercion using functions like toIntegerOrNull() and toFloatOrNull() to ensure data integrity. \n- [EXTERNAL_DOWNLOADS]: The skill references external tools and repositories for installation and data management that are owned by the vendor. \n
- Installation: The README provides an npx command to add the skill from the author's GitHub repository (github.com/neo4j-contrib/neo4j-skills). \n
- Tools: Links to the official Neo4j Data Importer GUI (data-importer.neo4j.io) and documentation are provided for user guidance.
Audit Metadata