china-stock-analysis
Pass
Audited by Gen Agent Trust Hub on Mar 30, 2026
Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill executes local Python scripts including 'stock_screener.py', 'data_fetcher.py', 'financial_analyzer.py', and 'valuation_calculator.py' to perform data fetching, processing, and financial modeling.
- [EXTERNAL_DOWNLOADS]: The skill requires the installation of external Python packages 'akshare', 'pandas', and 'numpy'. These are standard libraries for financial data analysis and do not pose an inherent risk when retrieved from official registries.
- [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection (Category 8) because it processes untrusted data from external financial APIs.
- Ingestion points: Data is ingested via 'akshare' in 'scripts/data_fetcher.py', retrieving company information, financial statements, and market news.
- Boundary markers: No specific boundary markers or 'ignore' instructions are present to prevent the agent from being influenced by malicious content embedded in the financial data strings.
- Capability inventory: The skill can execute Python scripts, read/write local JSON and Markdown files, and present processed information to the user.
- Sanitization: While numeric data is parsed into floats, textual data from external sources is interpolated into the final analysis reports without sanitization against potential prompt injection attacks.
Audit Metadata