a-share-analysis

Pass

Audited by Gen Agent Trust Hub on Feb 17, 2026

Risk Level: SAFENO_CODE
Full Analysis
  • [Prompt Injection] (SAFE): The skill consists of neutral instructional content for financial analysis and does not contain any patterns aimed at bypassing agent constraints or overriding instructions.
  • [Data Exposure & Exfiltration] (SAFE): No hardcoded credentials, sensitive file paths, or unauthorized network exfiltration patterns were identified.
  • [Unverifiable Dependencies & Remote Code Execution] (SAFE): The skill contains no code files or requests for external package installations.
  • [Indirect Prompt Injection] (SAFE): The skill is designed to process external financial data from sources like East Money and Xueqiu (Ingestion points: web search via SKILL.md). While it lacks explicit boundary markers or sanitization, it has no hazardous capabilities such as system file access or command execution (Capability inventory: None), rendering the surface area benign.
Audit Metadata
Risk Level
SAFE
Analyzed
Feb 17, 2026, 05:19 PM