crypto-advisor

Pass

Audited by Gen Agent Trust Hub on Jun 16, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill implements a robust set of safety invariants, including mandatory disclaimers, explicit sizing rules, and a strict 'no leverage' policy for all recommendations. These constraints are designed to limit financial risk and ensure transparency.
  • [SAFE]: No obfuscation, hardcoded credentials, or suspicious network operations were detected within the skill's instructions or metadata.
  • [SAFE]: External capabilities are limited to calling internal sub-skills for data analysis (e.g., 'analyst-crypto', 'fomc-monitor') and a connector for generating trade notifications. It does not execute arbitrary shell commands or remote code.
  • [PROMPT_INJECTION]: The skill processes user questions about cryptocurrency, creating a surface for indirect prompt injection. However, it mitigates this risk by requiring 'no fabrication' of data, using a human-in-the-loop 'notification-first' model, and anchoring responses to specific invariants and a 'backtest gate'.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 16, 2026, 08:03 AM
Security Audit — agent-trust-hub — crypto-advisor