alchemy-mcp

Warn

Audited by Snyk on Apr 21, 2026

Risk Level: MEDIUM
Full Analysis

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

  • Third-party content exposure detected (high risk: 0.90). The skill's SKILL.md explicitly instructs the agent to call Data/RPC tools (e.g., getNFTMetadata, getNFTsForOwner, getFloorPrice and other Data tools listed under "Run tools" and the "Tool catalog") that fetch public blockchain/NFT/marketplace metadata and marketplace-derived prices — user-generated and public third-party content the agent is expected to read and which can materially influence subsequent actions.

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

  • Potentially malicious external URL detected (high risk: 0.80). The skill explicitly requires connecting at runtime to the MCP server https://mcp.alchemy.com/mcp, which provides tool definitions and executes remote tool calls that directly control agent behavior and perform remote operations, so this URL is a runtime dependency that can control prompts/actions.

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

  • Direct money access detected (high risk: 1.00). The skill is explicitly a blockchain/crypto execution and administration tool. It exposes on-chain JSON-RPC and Alchemy-specific tools (RPC: ethGetBalance, ethCall, ethCallBundle, simulateExecution, simulateAssetChanges, traceTransaction, debugTraceTransaction; ERC-4337 account-abstraction tools like estimateUserOperationGas, requestGasAndPaymasterAndData; Solana RPC tools such as solana_simulateTransaction; plus app admin tools like create_app, select_app, update_allowlist). These are specific crypto/blockchain APIs designed for inspecting, simulating, managing, and operating on on-chain accounts and user operations (i.e., the kinds of calls used to construct/sign/send transactions and manage apps). Because the skill is specifically designed for crypto transaction and account operations (not a generic browser or HTTP tool), it provides direct financial execution capability for blockchain assets.

Issues (3)

W011
MEDIUM

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

W012
MEDIUM

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

W009
MEDIUM

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

Audit Metadata
Risk Level
MEDIUM
Analyzed
Apr 21, 2026, 07:45 PM
Issues
3