gate-exchange-trading-copilot

Pass

Audited by Gen Agent Trust Hub on Mar 16, 2026

Risk Level: SAFEPROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
  • [PROMPT_INJECTION]: The skill analyzes untrusted external data from news and social media sources to inform trading decisions. This creates a surface for indirect prompt injection where malicious content in these sources could attempt to influence the agent's actions.
  • Ingestion points: External news articles and social media posts retrieved during the analysis phase (e.g., via news_feed_search_news).
  • Boundary markers: The skill does not specify the use of delimiters or 'ignore' instructions when processing this external data.
  • Capability inventory: The skill possesses high-impact execution capabilities, including the ability to place, amend, and cancel spot and futures orders on Gate Exchange (cex_spot_create_spot_order, cex_fx_create_fx_order).
  • Sanitization: No explicit validation or filtering of external data content is documented in the skill's instructions.
  • [COMMAND_EXECUTION]: The skill orchestrates trade execution on Gate Exchange using authenticated tools. While this is the primary purpose of the skill, the execution of financial commands is a sensitive capability. The skill mitigates this risk by enforcing a strict workflow: it must produce a 'Trading Brief' and an 'Order Draft', and then wait for explicit, immediate confirmation from the user before calling any execution tools.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 16, 2026, 03:18 AM