jupiter

Pass

Audited by Gen Agent Trust Hub on Apr 21, 2026

Risk Level: SAFE
Full Analysis
  • [PROMPT_INJECTION]: No malicious injection patterns detected. The skill contains robust safety instructions, explicitly requiring user confirmation before executing on-chain operations and limiting tool invocations per request.
  • [DATA_EXFILTRATION]: No data exfiltration risks identified. Network activity is confined to the official Jupiter API (lite-api.jup.ag) via a proxy client. The skill handles only public blockchain data like mint addresses and transaction payloads; no private keys or sensitive credentials are hardcoded or accessed.
  • [REMOTE_CODE_EXECUTION]: No patterns for remote code execution were found. The skill does not use eval, exec, or dynamic loading of untrusted content.
  • [COMMAND_EXECUTION]: The skill does not perform any arbitrary command line execution. Scripts are dedicated to structured API interaction and data formatting.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 21, 2026, 03:22 PM