stock-analysis

Pass

Audited by Gen Agent Trust Hub on Mar 4, 2026

Risk Level: SAFEPROMPT_INJECTIONCOMMAND_EXECUTIONEXTERNAL_DOWNLOADS
Full Analysis
  • [PROMPT_INJECTION]: The skill presents an indirect prompt injection surface as it retrieves and processes news from external sources and incorporates it into the AI analysis prompt.\n
  • Ingestion points: News summaries are collected from the WebSearch tool and external APIs in references/stock_data_fetcher.py.\n
  • Boundary markers: The references/analysis-prompt-template.md lacks explicit delimiters or instructions to ignore embedded commands in the news text.\n
  • Capability inventory: The skill has access to the Bash tool, which is used to execute data-fetching scripts and manage system dependencies.\n
  • Sanitization: News content is truncated to a specific length but is not filtered for potential injection strings.\n- [COMMAND_EXECUTION]: The skill executes system commands via the Bash tool to facilitate its operations.\n
  • Evidence: SKILL.md uses Bash to install Python dependencies and to run the stock_data_fetcher.py script from a temporary directory.\n- [EXTERNAL_DOWNLOADS]: The skill downloads third-party libraries from the Python Package Index (PyPI) at runtime.\n
  • Evidence: The installation of akshare, yfinance, and efinance is performed via pip3 commands in SKILL.md. These are recognized libraries for financial data retrieval.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 4, 2026, 02:27 PM