senpi-trade
Pass
Audited by Gen Agent Trust Hub on Sep 23, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and act upon data from third-party trader profiles, creating a surface for potential indirect prompt injection during mirroring operations. \n
- Ingestion points: Trader wallet addresses and current position data retrieved from external sources and the Hyperliquid exchange (defined in SKILL.md under Branch B). \n
- Boundary markers: The skill's instructions strictly mandate a multi-step interview process and require an explicit "yes" confirmation from the user before executing any financial tools. \n
- Capability inventory: The skill utilizes powerful financial tools for creating, funding, and managing trading positions (e.g., strategy_create, create_position, edit_position). \n
- Sanitization: It implements a mandatory pre-funding simulation via the execution_estimate_position_opening tool and requires vetting through the senpi-trader-research skill to analyze trader performance and risk metrics before execution.
Audit Metadata