bingx-copytrade-spot

Pass

Audited by Gen Agent Trust Hub on Sep 17, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill ingests and displays external data from BingX API endpoints (trading overview, profit history, and order details), creating a surface for potential indirect instructions.
  • Ingestion points: Data is retrieved from various BingX API endpoints through the fetchSigned function implemented in SKILL.md.
  • Boundary markers: The instructions do not specify the use of delimiters or boundary markers to isolate API-returned data from the agent's internal reasoning or system instructions.
  • Capability inventory: The skill possesses the capability to execute sell orders through the POST /openApi/copyTrading/v1/spot/trader/sellOrder endpoint defined in SKILL.md and api-reference.md.
  • Sanitization: The skill employs a validateParams function in SKILL.md that sanitizes user input by rejecting characters commonly used in URL manipulation or injection, such as &, =, ?, and #.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 17, 2026, 04:57 PM
Security Audit — agent-trust-hub — bingx-copytrade-spot