skills/jeremylongshore/claude-code-plugins-plus-skills/generating-trading-signals/Gen Agent Trust Hub
generating-trading-signals
Pass
Audited by Gen Agent Trust Hub on Mar 11, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill fetches historical price and volume data from Yahoo Finance via the
yfinancePython library. This is a well-known financial data service, and the operation is central to the skill's primary purpose. - [COMMAND_EXECUTION]: The skill uses Python scripts (
scanner.py,indicators.py, andsignals.py) to perform calculations and manage data caching. These scripts are executed locally via the agent's Bash tool to process market data and generate signal reports. - [PROMPT_INJECTION]: The skill possesses an indirect prompt injection surface as it processes external market data from an API and generates natural language 'reasoning' strings for the agent. However, the risk is negligible as the data ingested is limited to numerical financial metrics from a reputable source.
- Ingestion points:
scripts/scanner.py(viayfinanceAPI calls). - Boundary markers: Absent; the output results are presented in plain text tables or JSON without explicit isolation delimiters.
- Capability inventory: File system write access (for caching and JSON output) and Python execution via Bash.
- Sanitization: The scripts focus on numerical data validation and error handling for API responses, though no specific sanitization for natural language injection is required for this data type.
Audit Metadata