trade-signal
Pass
Audited by Gen Agent Trust Hub on Jun 16, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [SAFE]: No malicious patterns or security vulnerabilities were identified in the skill logic. The workflow uses platform-specific tools for market data and position tracking in a simulated environment.
- [PROMPT_INJECTION]: The skill processes untrusted data which could lead to indirect prompt injection. 1. Ingestion points: User input is ingested via the $ARGUMENTS variable in SKILL.md. 2. Boundary markers: No delimiters or explicit warnings are used to separate user data. 3. Capability inventory: The skill invokes TradingMarket, TradingOpenPosition, and TradingPortfolio. 4. Sanitization: No sanitization or validation of the input is performed before it is used to populate trade rationales. While this represents a surface for manipulation, the scope is restricted to paper trading with no access to sensitive data or real financial assets.
Audit Metadata