bybit-v5
Pass
Audited by Gen Agent Trust Hub on Mar 6, 2026
Risk Level: SAFE
Full Analysis
- [CREDENTIALS_UNSAFE]: The skill manages sensitive API keys and secrets but implements strong risk-reduction measures. It mandates that the agent mask credentials when displayed to the user (e.g., showing only the last 5 characters) and directs that actual keys be stored in a dedicated TOOLS.md file rather than being hardcoded in scripts or the skill body.\n- [COMMAND_EXECUTION]: The skill uses Bash command examples involving
curlandopensslto demonstrate how to perform authenticated requests and generate HMAC-SHA256 signatures. These operations are standard for secure interaction with financial exchange APIs.\n- [EXTERNAL_DOWNLOADS]: All network operations target official Bybit domains (e.g.,api.bybit.com,api.bybit-tr.com). These are recognized as legitimate vendor resources and do not represent a threat of exfiltration or unauthorized code execution.\n- [PROMPT_INJECTION]: A potential surface for indirect prompt injection exists because the skill processes external data such as market announcements. However, this risk is effectively mitigated by the skill's instruction that any 'write' operation (e.g., placing orders or withdrawing funds) on the mainnet must require the user to explicitly type 'CONFIRM'.\n - Ingestion points: The
/v5/announcements/indexand market data endpoints ingest text data from the exchange.\n - Boundary markers: Not explicitly defined in the prompt logic.\n
- Capability inventory: The skill possesses high-privilege capabilities including trade execution, position management, and asset transfers.\n
- Sanitization: No explicit sanitization or filtering of API response content is described.
Audit Metadata