clanker-plugin

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

• Third-party content exposure detected (medium risk: 0.30). The workflow queries external APIs (clanker.world/api) and on-chain contract data (list-tokens, search-tokens) where third-party token names, descriptions, and metadata returned can contain outsider-authored free text ingested by the agent.

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

• Direct money access detected (high risk: 0.70). The skill implements direct financial operations (deploy-token and claim-rewards) that initiate on-chain transactions and token deployments via onchainos wallet contract-call. Because these transaction-signing and broadcasting actions rely entirely on agent instructions and prompt-based confirmation gates rather than an independent service/execution-layer authentication or authorization check for the financial execution route, the control standard is not satisfied.