vechain-core

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 and references/resources.md explicitly require using public MCP servers and external documentation (e.g., @vechain/mcp-server, Kapa.ai MCP, https://docs.vechainkit.vechain.org, vechain.energy, and public token-registry JSON) to fetch live VeChain docs and blockchain data that the agent must read and which can materially influence transaction-building and delegation decisions.

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

• Potentially malicious external URL detected (high risk: 0.90). The skill explicitly instructs running remote code via "npx -y @vechain/mcp-server@latest" (pulling/executing a package from the npm registry) and configures runtime MCP endpoints the agent will query (e.g., https://vechain.mcp.kapa.ai and https://docs.vechainkit.vechain.org/~gitbook/mcp), which are external runtime dependencies that can supply instructions/data directly used by the agent.

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

• Direct money access detected (high risk: 1.00). The skill is explicitly for VeChain blockchain development and includes transaction building and execution capabilities: SDK usage for on-chain operations, use of @vechain/mcp-server for on-chain data and transaction building, multi-clause (batched) transactions, fee delegation/gasless transactions (VIP-191), and explicit guidance about gas, signing, and token transfers (VET/VTHO). Those are specific crypto/blockchain transaction and signing features that can move value. This meets the "Crypto/Blockchain (Wallets, Swaps, Signing)" criterion for Direct Financial Execution.