flare-ftso

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

• Third-party content exposure detected (high risk: 0.80). The skill explicitly fetches and consumes untrusted public onchain FTSO data from Flare RPC endpoints and ContractRegistry-resolved FtsoV2 calls (e.g., getFeedsById/getFeedById in scripts/read-feeds-offchain.ts and scripts/consume-feeds.sol, and FeedDataWithProof accepted by savePrice), which the agent is expected to interpret and which can materially influence subsequent transactions or actions.

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

• Direct money access detected (high risk: 1.00). The skill is explicitly about integrating with the Flare blockchain FTSO contract and includes onchain, payable operations and value-transfer actions. It documents payable contract methods (e.g. getFeedsById{value: fee}), fee calculation via IFeeCalculator, and making volatility incentives via FastUpdatesIncentiveManager.offerIncentive with msg.value. It also discusses delegation/staking (delegators earning rewards) and provides example scripts for invoking these contract calls. These are explicit crypto/blockchain financial execution capabilities (sending value / performing onchain payable calls), not merely generic documentation or browsing. Therefore it grants Direct Financial Execution authority.