solana-agent-kit
Pass
Audited by Gen Agent Trust Hub on Jun 20, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The documentation provides instructions to download and execute an installation script (
install.sh) from the official GitHub repository of the vendor (sendaifun/solana-mcp). This is the standard method for installing the Model Context Protocol (MCP) server component. - [COMMAND_EXECUTION]: The provided templates and examples demonstrate the execution of blockchain operations (e.g., token transfers, swaps, and deployments) via shell commands or script execution. These operations are the primary intended purpose of the toolkit.
- [PROMPT_INJECTION]: The skill architecture facilitates the creation of agents that ingest untrusted user input to perform high-stakes blockchain operations. While the templates include system prompts with safety guidelines—such as requiring confirmation for large transactions—the ingestion of external data from RPC providers and user prompts constitutes an indirect prompt injection attack surface.
Audit Metadata