skills/plurigrid/asi/aptos-wallet-mcp/Gen Agent Trust Hub

aptos-wallet-mcp

Pass

Audited by Gen Agent Trust Hub on Feb 17, 2026

Risk Level: SAFE
Full Analysis
  • SAFE (SAFE): The skill follows secure template practices by using environment variable placeholders (e.g., ${ALICE_APTOS_KEY}) instead of hardcoding sensitive private keys or tokens. It references local script paths for execution rather than remote URLs.
  • Indirect Prompt Injection (LOW): The skill interacts with external blockchain data which could potentially contain malicious instructions, though this is a common risk for blockchain tools.
  • Ingestion points: Data returned from tools like aptos_view, aptos_balance, and aptos_pending which query the blockchain.
  • Boundary markers: None identified in the provided configuration.
  • Capability inventory: The skill has the capability to execute local Node.js scripts and perform financial transactions (transfers, swaps, stakes) if authorized.
  • Sanitization: Not present in the configuration files; reliance is placed on the underlying MCP server implementation.
Audit Metadata
Risk Level
SAFE
Analyzed
Feb 17, 2026, 06:37 PM