blofin-asset-manager
Pass
Audited by Gen Agent Trust Hub on Mar 10, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill requires sensitive credentials (BLOFIN_API_KEY, BLOFIN_API_SECRET, BLOFIN_PASSPHRASE) stored in environment variables. While necessary for the skill's functionality, these are high-value targets. The skill includes explicit instructions for the agent to avoid disclosing these keys or withdrawal addresses in logs.
- [SAFE]: For sensitive operations like fund_transfer, the skill includes a mandatory confirmation step, requiring the agent to verify all transfer details with the user before execution. This mitigates the risk of accidental or unauthorized fund movement.
- [PROMPT_INJECTION]: The skill retrieves data from external API endpoints (transfer history, deposits, withdrawals) which is then processed by the agent. This represents an indirect prompt injection surface where instructions could theoretically be embedded in transaction metadata.
- Ingestion points: get_fund_transfer_history, get_deposit_history, and get_withdrawal_history in SKILL.md.
- Boundary markers: Absent.
- Capability inventory: The skill has the capability to perform fund transfers between internal accounts.
- Sanitization: No explicit sanitization or filtering of API response content is described in the skill definition.
Audit Metadata