blockscout-analysis

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

• Third-party content exposure detected (low risk: 0.10). The agent skill queries blockchain data via the Blockscout MCP Server and REST API (as well as Chainscout), where blockchain data like token names and NFT metadata can contain outsider-authored text, but the agent actively queries specific items and addresses rather than monitoring an unvetted public feed.