stock-screener

Pass

Audited by Gen Agent Trust Hub on Sep 25, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill utilizes industry-standard libraries for data processing.\n
  • Evidence: pandas and numpy are listed in scripts/requirements.txt and imported in scripts/stock_screener.py.\n- [INDIRECT_PROMPT_INJECTION]: The skill provides an interface for processing external stock data, which constitutes a potential injection surface.\n
  • Ingestion points: Data is loaded from external CSV files using the load_csv method in scripts/stock_screener.py.\n
  • Boundary markers: The skill does not employ specific delimiters or instruction-ignoring directives for the external data.\n
  • Capability inventory: The skill allows for local file read and write operations via pandas; it does not possess network access or arbitrary command execution capabilities.\n
  • Sanitization: Numeric fields are parsed to float/int, providing natural validation for those fields, but textual metadata (e.g., sector, company name) is not explicitly sanitized for prompt-like content.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 25, 2026, 08:05 AM
Security Audit — agent-trust-hub — stock-screener