skills/helius-labs/core-ai/build/Gen Agent Trust Hub

build

Pass

Audited by Gen Agent Trust Hub on Nov 4, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill serves as a technical reference for Solana developers. All referenced external domains (e.g., helius.dev, helius-rpc.com, helius.xyz) and tools (e.g., helius-mcp, helius-cli, helius-sdk) are official resources belonging to the vendor, Helius Labs.
  • [CREDENTIALS_SAFE]: The instructions explicitly warn against hardcoding API keys and recommend using environment variables or the vendor's dedicated configuration tools. Authentication tokens and local keypairs are stored in standard, user-controlled paths (e.g., ~/.helius/), which is consistent with the behavior of professional development CLI tools.
  • [COMMAND_EXECUTION]: The skill documents the use of official Helius CLI commands and the installation of the Helius MCP server via npx. These commands are legitimate setup steps for the infrastructure described.
  • [EXTERNAL_DOWNLOADS]: The skill mentions official SDKs and packages available through standard registries (NPM). These are trusted dependencies for the Solana development ecosystem.
  • [INDIRECT_PROMPT_INJECTION]: As a tool that queries and displays blockchain data (such as transaction descriptions and account history), the skill has an inherent surface for indirect prompt injection from malicious on-chain data. However, this is a known risk for blockchain explorers and agents, and the skill's reliance on structured APIs and the vendor's parsing engine mitigates this risk to a low level.
Audit Metadata
Risk Level
SAFE
Analyzed
Nov 4, 2026, 03:17 AM