generating-trading-signals
Pass
Audited by Gen Agent Trust Hub on Feb 27, 2026
Risk Level: SAFEPROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [PROMPT_INJECTION]: Potential for indirect prompt injection via ingestion of external market data.
- Ingestion points: The
fetch_datafunction inscripts/scanner.pyretrieves historical price data from Yahoo Finance using theyfinancelibrary. - Boundary markers: No explicit delimiters or instructions to ignore embedded content are used for data fetched from external sources.
- Capability inventory: The skill utilizes
Bash(python:*)to execute its analysis scripts andRead/Writetools for caching data and saving results. - Sanitization: Data is processed primarily as numeric values for technical indicator calculations using
pandasandnumpy, which significantly reduces the risk of interpreting text as commands. - [COMMAND_EXECUTION]: The skill facilitates integration with external tools by suggesting the execution of a backtesting script located in a sibling directory. This behavior is documented and uses predictable local file paths.
Audit Metadata