dexpaprika-api

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

• Third-party content exposure detected (high risk: 0.70). The skill explicitly pulls public DeFi data from the external DexPaprika MCP server (https://mcp.dexpaprika.com/sse) and exposes the agent to live, user-generated token/pool/transaction metadata via tools like getTokenDetails and getPoolTransactions, which the agent is expected to read and which can materially influence decisions.

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

• Potentially malicious external URL detected (high risk: 0.90). The skill requires adding the MCP SSE server https://mcp.dexpaprika.com/sse to its runtime config, and that server advertises "capabilities" and "workflow examples" which can supply instructions/workflows at runtime and thus directly influence agent prompts and behavior.