transfer
Pass
Audited by Gen Agent Trust Hub on Oct 1, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill ingests untrusted data through CLI arguments including --recipient and --memo in transfer.ts. The agent instructions lack explicit boundary markers or sanitization for these string inputs. The skill provides the capability to broadcast transactions via transferStx and tokensService.transfer, which represents a potential attack surface for indirect prompt injection targeting the wallet or downstream explorers.
- [COMMAND_EXECUTION]: The skill allows an agent to broadcast transactions for STX, fungible tokens, and NFTs. This intended functionality involves critical write access to the blockchain and requires user oversight to prevent unauthorized transfers.
- [SAFE]: The skill references the Hiro Explorer (explorer.hiro.so) for transaction verification. This is a standard and safe service integration within the Stacks blockchain ecosystem.
Audit Metadata