smart-money-signal-copy-trade

Pass

Audited by Gen Agent Trust Hub on Apr 28, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill implements a legitimate Solana trading bot with extensive safety logic located in risk_check.py. It includes comprehensive risk disclosures and requires explicit user confirmation before enabling live trading.
  • [COMMAND_EXECUTION]: The bot interacts with the onchainos CLI using the subprocess module. These interactions are implemented securely using argument lists, which prevents command injection vulnerabilities.
  • [PROMPT_INJECTION]: The SKILL.md instructions guide the AI agent through a structured interaction protocol with the user. No attempts to override safety filters or extract system prompts were found.
  • [EXTERNAL_DOWNLOADS]: No external code or scripts are downloaded at runtime. The skill utilizes the Python standard library and the pre-installed onchainos CLI.
  • [DATA_EXFILTRATION]: There is no evidence of unauthorized data transmission. The skill hosts a local dashboard on localhost:3248, but this is bound to the loopback interface and is used only for displaying trade status to the local user.
  • [CREDENTIALS_UNSAFE]: The skill does not store or hardcode private keys or API tokens. It uses the onchainos Agentic Wallet, which keeps signing keys within a secure Trusted Execution Environment (TEE).
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 28, 2026, 01:50 PM