china-model-update

Pass

Audited by Gen Agent Trust Hub on Jun 13, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSDATA_EXFILTRATIONPROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill utilizes the AkShare library, a well-known open-source financial data interface, to fetch market data and financial statements.
  • [DATA_EXFILTRATION]: The skill performs legitimate network operations to retrieve financial data from established services, including iFind (MCP) and AkShare, as well as official disclosure platforms like 巨潮资讯 (CNInfo).
  • [PROMPT_INJECTION]: The skill ingests untrusted external content such as earnings call transcripts and management commentary. While this creates a theoretical surface for indirect prompt injection, the risk is inherent to the financial analysis use case and the skill includes quality control checklists to verify data integrity.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 13, 2026, 01:06 PM
Security Audit — agent-trust-hub — china-model-update