strk20-privacy-sdk

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

• Third-party content exposure detected (low risk: 0.10). The required workflow uses an IndexerDiscoveryProvider and ProvingServiceProofProvider over HTTP/OHTTP to fetch notes and state, which could ingest outsider-submitted data if connected to an untrusted indexer.

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

• Potentially malicious external URL detected (medium risk: 0.30). The skill contains instructions and code snippets referencing an external GitHub repository and git-based dependency installation (npm install "starkware-libs/starknet-privacy#<commit-sha>"), which constitutes a common/reputable unofficial operational dependency.

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

• Direct money access detected (high risk: 1.00). The skill contains specific documentation and configuration examples for crypto/blockchain financial tools and SDKs (Starknet Privacy SDK, handling private transfers, deposits, withdrawals, wallets, and signing transactions via account.execute). This constitutes direct financial execution capability involving cryptocurrency assets and smart contract transactions.