multiversx-blockchain-data

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

• Third-party content exposure detected (high risk: 0.80). The skill reads public on‑chain, user-provided data via self.blockchain() (notably get_esdt_token_data, get_token_attributes and the uris field in EsdtTokenData), which are untrusted, third‑party metadata that the agent is expected to read and interpret.