aibtc-bitcoin-wallet

Pass

Audited by Gen Agent Trust Hub on May 9, 2026

Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill recommends installation via npx to execute the vendor's official package, @aibtc/mcp-server.
  • [EXTERNAL_DOWNLOADS]: The skill connects to vendor-controlled domains (aibtc.com, pillarbtc.com) and the x402 protocol relay for agent registration, activity check-ins, and transaction sponsorship.
  • [PROMPT_INJECTION]: The skill manages an indirect prompt injection surface by processing external data during message signing and inbox operations.
  • Ingestion points: External message content provided to btc_sign_message, inbox content in send_inbox_message, and data retrieved from x402 API endpoints.
  • Boundary markers: Explicit boundary markers are not documented for prompt interpolation in the instruction files.
  • Capability inventory: The skill possesses high-impact capabilities including fund transfers (transfer_btc, transfer_stx) and wallet management (wallet_unlock).
  • Sanitization: Risk is mitigated by the 'probe-before-pay' workflow and instructions requiring explicit human-in-the-loop approval before executing payments or high-impact actions.
Audit Metadata
Risk Level
SAFE
Analyzed
May 9, 2026, 05:51 AM