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 likemidPrice,getLevel2TicksFromMid, andaccountfetch 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 usingsignAndExecuteTransaction, which involves financial operations. - Sanitization: No data validation or sanitization processes are mentioned for the retrieved blockchain data.
Audit Metadata