swig-smart-wallet

Fail

Audited by Snyk on Feb 26, 2026

Risk Level: HIGH
Full Analysis

HIGH W007: Insecure credential handling detected in skill instructions.

  • Insecure credential handling detected (high risk: 1.00). The skill explicitly tells the agent to ask the user for Paymaster API keys and other secret values and to store them (e.g., in a .env), which requires the LLM to accept and could lead to outputting those secrets verbatim.

MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).

  • Third-party content exposure detected (high risk: 0.80). The skill explicitly asks for a Solana RPC endpoint (e.g., public mainnet/devnet or custom RPC like Helius/Triton) and instructs the agent to call/fetch on-chain state via fetchSwig/refetch and to interact with external endpoints (user-provided sponsorUrl and the Swig Paymaster API/dashboard.onswig.com), so it ingests untrusted public blockchain/RPC and arbitrary URL responses that directly influence decisions and transactions.

MEDIUM W012: Unverifiable external dependency detected (runtime URL that controls agent).


MEDIUM W009: Direct money access capability detected (payment gateways, crypto, banking).

  • Direct money access detected (high risk: 1.00). The skill is explicitly designed to create and manage on-chain Solana smart wallets and to execute signed transactions that move SOL/tokens. It includes concrete APIs and flows for: generating keypairs, wrapping and sending transfer instructions (SystemProgram.transfer), using paymaster clients (createPaymasterClient, signAndSend / fullySign), sponsoring transactions via a gas server (API endpoints), and verifying balances. These are specific crypto/blockchain wallet and transaction-execution capabilities (not generic). Therefore it grants direct financial execution authority.
Audit Metadata
Risk Level
HIGH
Analyzed
Feb 26, 2026, 04:30 AM