neo4j-import-skill
Pass
Audited by Gen Agent Trust Hub on May 6, 2026
Risk Level: SAFE
Full Analysis
- [COMMAND_EXECUTION]: The skill utilizes the Bash tool for legitimate data preparation tasks, such as encoding checks using
fileandiconv, row counting withwc, and database administration using the officialneo4j-adminutility. These operations are standard for the skill's purpose and are documented with clear usage gates. - [EXTERNAL_DOWNLOADS]: The skill provides patterns for importing data from various external sources, including public cloud storage (AWS S3, Google Cloud Storage, Azure Blob Storage) and HTTPS endpoints for JSON/CSV data. These references are used for data ingestion and do not involve downloading or executing untrusted scripts.
- [PROMPT_INJECTION]: The instructions explicitly mandate a human-in-the-loop verification step (a 'write execution gate') before any bulk write operations or schema changes are performed via MCP tools, effectively mitigating risks of unauthorized execution.
- [CREDENTIALS_UNSAFE]: The skill promotes secure development practices by instructing users to manage credentials via environment variables and providing only generic placeholders (e.g., 'xxx', 'password') in its code examples.
Audit Metadata