deepbookv3-query-the-pool
Pass
Audited by Gen Agent Trust Hub on Sep 4, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill facilitates the retrieval of data from external blockchain sources (DeepBook V3 pools). This external data, such as token names or pool identifiers, is untrusted and could theoretically contain malicious instructions designed to influence the agent's behavior.
- Ingestion points: SDK functions
getLevel2Ticks,getAmountOut, andgetLockedBalanceinSKILL.mdingest external pool and balance data. - Boundary markers: Not present in the provided code snippets.
- Capability inventory: Read-only SDK queries for blockchain state.
- Sanitization: No sanitization logic for external blockchain data is included in the provided examples.
Audit Metadata