trading-expert
Pass
Audited by Gen Agent Trust Hub on Sep 18, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill implements a framework for processing external market data (ticks and quotes), which creates a potential surface for indirect instructions if the data source is untrusted.
- Ingestion points: The MarketDataProcessor.process_tick method in SKILL.md ingests tick data as dictionaries.
- Boundary markers: Not explicitly implemented within the data processing logic.
- Capability inventory: The skill environment allows Bash(python:*), Read, Write, and Edit tools.
- Sanitization: RiskManager.validate_order provides pre-trade checks to ensure order parameters are within safe bounds.
Audit Metadata