solana-mcp-vybe
Pass
Audited by Gen Agent Trust Hub on Sep 16, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSREMOTE_CODE_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill instructions configure the MCP client to fetch resource definitions and tool metadata from a remote server located at
https://mcp.vybenetwork.xyz. - [REMOTE_CODE_EXECUTION]: The setup guide for Claude Desktop recommends using
npx mcp-remoteto connect to and execute tools hosted on the remote Vybe infrastructure. - [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and process data from the Solana blockchain, which is an untrusted third-party source.
- Ingestion points: Blockchain data such as account information, transaction logs, and token metadata retrieved through RPC tools like
solana_get_token_metadataandsolana_get_transaction. - Boundary markers: No specific delimiters or safety instructions are provided to help the agent distinguish between data and potential instructions embedded in blockchain fields.
- Capability inventory: The agent is empowered to make network calls to the remote MCP server and perform logic based on the untrusted data returned.
- Sanitization: The documentation does not specify any sanitization or validation logic for the content fetched from the blockchain.
Audit Metadata