solana-toolkit-guide

Pass

Audited by Gen Agent Trust Hub on Jun 21, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill instructs users to build a Rust implementation using cargo build and execute toolkit functions through npx and node worker threads.
  • [EXTERNAL_DOWNLOADS]: The skill installs the @nirholas/solana-wallet-toolkit package from the NPM registry to provide the core TypeScript functionality and MCP integration.
  • [DATA_EXPOSURE]: The documentation includes examples for mnemonic-based wallet restoration. While this is a standard feature of a wallet toolkit, it involves the handling of highly sensitive cryptographic seeds within the agent's context.
  • [INDIRECT_PROMPT_INJECTION]: The skill presents an attack surface where untrusted data could be processed.
  • Ingestion points: Custom prefixes provided to generateVanityAddress and seed phrases provided to Wallet.fromMnemonic (SKILL.md).
  • Boundary markers: None identified in the provided instructions to distinguish between data and commands.
  • Capability inventory: The skill provides capabilities to generate wallets, search for vanity addresses, and interface with an MCP server (SKILL.md).
  • Sanitization: No explicit sanitization or validation of input data is documented within the skill body.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 21, 2026, 03:13 AM
Security Audit — agent-trust-hub — solana-toolkit-guide