stock-daytrading
Pass
Audited by Gen Agent Trust Hub on Aug 20, 2026
Risk Level: SAFE
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes market data from external sources (Alpaca/yfinance), which represents an attack surface for untrusted data input. * Ingestion points: Market data feeds from Alpaca and yfinance (SKILL.md). * Boundary markers: None explicitly defined in the prompt text. * Capability inventory: Proposing and executing stock trades via Robinhood (SKILL.md). * Sanitization: The skill employs deterministic 'hard caps' and a mandatory human-in-the-loop approval step before any orders are placed, effectively mitigating the risk of automated manipulation.
Audit Metadata