neo4j-aura-provisioning-skill

Pass

Audited by Gen Agent Trust Hub on Apr 28, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill instructs the agent to install aura-cli via pip. This is the official Python-based command-line tool provided by Neo4j for interacting with the Aura service.
  • [COMMAND_EXECUTION]: The skill uses Bash commands for cloud resource management tasks, including instance creation, status monitoring, and authentication via OAuth. These commands are necessary for the skill's primary function.
  • [CREDENTIALS_UNSAFE]: The skill provides guidance on handling API credentials (Client ID and Secret). It correctly advises using environment variables for headless environments and provides instructions for creating a .env file and adding it to .gitignore to prevent secret leakage in version control systems.
  • [PROMPT_INJECTION]: The skill exposes a potential attack surface for indirect prompt injection by processing external data from the Neo4j Aura API and documentation.
  • Ingestion points: Data is ingested from the Neo4j Aura REST API responses and documentation via WebFetch and CLI tool output (SKILL.md).
  • Boundary markers: None identified in the current draft version.
  • Capability inventory: The skill has access to the Bash tool, allowing it to execute shell commands and modify the local filesystem (SKILL.md).
  • Sanitization: No specific sanitization or escaping of API-returned data is mentioned before processing.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 28, 2026, 04:43 PM