bitget
Pass
Audited by Gen Agent Trust Hub on Jun 13, 2026
Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill instructs users to install the bitget-client package globally via npm. This tool is the primary interface for the exchange and is provided by the skill author.
- [COMMAND_EXECUTION]: The skill relies on shell command execution via the bgc CLI to perform all exchange tasks, including high-risk financial operations like placing orders, transferring funds, and setting leverage.
- [PROMPT_INJECTION]: The skill is vulnerable to indirect prompt injection (Category 8) because it processes untrusted data from external API responses. Evidence Chain: 1. Ingestion point: JSON output from the bgc CLI tool. 2. Boundary markers: Absent; tool output is processed directly by the agent. 3. Capability inventory: The agent can execute arbitrary shell commands via the bgc CLI, including financial write operations. 4. Sanitization: No evidence of response sanitization or filtering before the agent processes the data.
Audit Metadata