skills/ppsteven/skills/akshare-data/Gen Agent Trust Hub

akshare-data

Pass

Audited by Gen Agent Trust Hub on Feb 27, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The script scripts/akshare_cli.py dynamically maps command-line arguments to functions within the akshare library using the inspect and argparse modules. This functionality is restricted to the akshare module namespace and is used to execute the library's data-fetching routines.
  • [EXTERNAL_DOWNLOADS]: The skill fetches financial data from numerous well-known technology and financial services (e.g., Sina Finance, EastMoney, Shanghai Stock Exchange). These external network operations are essential to the primary purpose of the skill and target established, reputable domains.
  • [PROMPT_INJECTION]: The skill possesses a data ingestion surface for external content, such as financial news and reports, which could serve as a vector for indirect prompt injection.
  • Ingestion points: Data is fetched from multiple external financial websites as documented in the references/ directory.
  • Boundary markers: Absent; the skill returns raw or formatted data directly from the source.
  • Capability inventory: The skill can perform network requests through the akshare library and output data to the console or files via CLI redirection.
  • Sanitization: None; the data is returned as-is from the data providers.
Audit Metadata
Risk Level
SAFE
Analyzed
Feb 27, 2026, 06:30 AM