upbit

Pass

Audited by Gen Agent Trust Hub on Sep 15, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill instructs users to install the @upbit-official/upbit-cli package from NPM. This is a vendor-owned package and is used as the primary interface for the skill. It also uses api.ipify.org to check the user's public IP for API allowlisting purposes, which is a common and safe practice.
  • [COMMAND_EXECUTION]: The skill uses the upbit CLI to perform exchange operations. It implements a safety rule requiring users to type 'CONFIRM' before any write operation (e.g., placing orders or initiating withdrawals), which provides a necessary security layer.
  • [INDIRECT_PROMPT_INJECTION]: The skill processes market data and account information from the Upbit API. While this presents an attack surface for indirect prompt injection via manipulated exchange data, the skill includes specific instructions to follow a terminology glossary and requires manual confirmation for sensitive actions, which effectively mitigates the risk.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 15, 2026, 09:23 AM
Security Audit — agent-trust-hub — upbit