xl1-patterns

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

• Third-party content exposure detected (high risk: 0.90). The skill's required workflows (e.g., "Chain Data Indexing — Protocol/Service" and examples like createRestDataLakeRunner('https://api.archivist.xyo.network/dataLake'), viewer.block.payloadsByHash, and gateway.addPayloadsToChain) explicitly fetch and ingest public on‑chain/off‑chain payloads (user-generated/untrusted) and then read/validate them to drive decisions and transaction submissions (settlement, attestations), so untrusted third‑party content can materially influence agent actions.

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

• Direct money access detected (high risk: 1.00). This skill is explicitly about building blockchain dApp features that move and manage on-chain assets: it defines atomic exchange / multi-party escrow flows, deploy/mint/transfer schemas for XRC-20 fungible tokens, single-step signed transfers, multi-signer BoundWitnesses, and headless verification that wires a seed-phrase wallet (GatewayBuilder.build(signer)). These are specific, application-level primitives for creating, signing, and settling asset transfers on XL1 (not generic tooling), so it grants direct financial execution capability.