portfolio-optimization

Pass

Audited by Gen Agent Trust Hub on Sep 16, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTION
Full Analysis
  • [SAFE]: The skill instructions and associated code recipes focus exclusively on financial modeling and portfolio optimization using vendor-supported libraries.
  • [EXTERNAL_DOWNLOADS]: The skill uses portfolio_optimization.utils.download_data to fetch financial market data from yfinance. This is a well-known service used for the skill's primary purpose, and the agent is instructed to obtain user permission before initiating the download.
  • [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted financial data from user-supplied CSV files or local datasets. Ingestion points: Data is loaded via utils.get_input_data from local paths or user-specified CSV files. Boundary markers: The instructions require validating that input data has numeric columns and a date-like index before return calculation. Capability inventory: The skill utilizes specialized mathematical libraries (cvxpy, cuopt); no arbitrary shell execution, unsafe deserialization, or unauthorized network operations are present. Sanitization: The instructions enforce numeric conversion and strict filtering/slicing of input DataFrames.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 16, 2026, 05:15 AM
Security Audit — agent-trust-hub — portfolio-optimization