deepbookv3-sdk-pools

Pass

Audited by Gen Agent Trust Hub on Sep 4, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill interacts with external data from the Sui blockchain, creating a vulnerability surface.
  • Ingestion points: In SKILL.md, methods like midPrice, getLevel2TicksFromMid, and account fetch external state.
  • Boundary markers: The instructions lack delimiters or safety warnings to ignore embedded commands in fetched data.
  • Capability inventory: In SKILL.md, the skill can build and execute transactions using signAndExecuteTransaction, which involves financial operations.
  • Sanitization: No data validation or sanitization processes are mentioned for the retrieved blockchain data.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 4, 2026, 03:04 PM
Security Audit — agent-trust-hub — deepbookv3-sdk-pools