phantom-wallet-mcp

Pass

Audited by Gen Agent Trust Hub on Jul 9, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill configuration specifies downloading and running the @phantom/mcp-server package from the NPM registry using npx.
  • [COMMAND_EXECUTION]: Execution of the npx -y @phantom/mcp-server command is required to start the MCP server within the agent's environment.
  • [INDIRECT_PROMPT_INJECTION]:
  • Ingestion points: The skill accepts untrusted data such as recipient addresses, token mints, and messages for signing through its tool parameters in SKILL.md.
  • Boundary markers: There are no explicit delimiters or instructions provided to the agent to ignore potentially malicious content embedded in the data it processes.
  • Capability inventory: The skill provides high-impact capabilities including token transfers, swaps, and transaction/message signing across Solana, Ethereum, Bitcoin, and Sui.
  • Sanitization: The instructions do not define any validation or sanitization steps for the data passed to the wallet tools.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 9, 2026, 10:45 PM
Security Audit — agent-trust-hub — phantom-wallet-mcp