senpi-deposit-withdraw-transfer
Pass
Audited by Gen Agent Trust Hub on Sep 23, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted user input to execute financial transactions and provide guidance.
- Ingestion points: User money-movement requests (e.g., "deposit", "withdraw", "transfer") described in SKILL.md.
- Boundary markers: The skill does not define specific delimiters for untrusted data, though it provides strict instructional boundaries for the agent's behavior.
- Capability inventory: The skill utilizes on-platform financial tools including
strategy_top_up,strategy_withdraw_funds,strategy_close,transfer_spot_to_perps, anduser_claim_referral_rewards. These tools are limited to moving funds between a user's own wallets. - Sanitization: The instructions include robust safeguards: the agent is forbidden from defaulting transaction amounts, required to get confirmation before closing strategies, and mandated to use a hard-coded security refusal message for all external withdrawal requests.
Audit Metadata