deepbook-overview

Pass

Audited by Gen Agent Trust Hub on Aug 21, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill serves as a documentation reference and architectural guide for DeepBook V3, focusing on educational content and technical specifications.
  • [EXTERNAL_DOWNLOADS]: The skill mentions the @mysten/deepbook-v3 Node package and the MystenLabs/deepbookv3 GitHub repository. These are official resources provided by the skill's author and are standard dependencies for the platform.
  • [COMMAND_EXECUTION]: Provides standard npm install instructions for the project's official SDK. These commands are benign and necessary for the described development workflow.
  • [DATA_EXFILTRATION]: The skill contains public blockchain identifiers, including package IDs, pool IDs, and token addresses. These are public-facing constants required for chain interaction and do not constitute sensitive data exposure.
  • [INDIRECT_PROMPT_INJECTION]: Mentions an external documentation search endpoint (sui.mcp.kapa.ai). This represents a potential surface for indirect prompt injection if the external service provides untrusted content, though it is recommended here as a legitimate tool for technical verification.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 21, 2026, 06:33 PM
Security Audit — agent-trust-hub — deepbook-overview