shiliu

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

• Third-party content exposure detected (low risk: 0.10). The skill reads third-party creator profiles, posts, and benchmark content via search and lookup endpoints like POST /api/v2/creator-lookups and creator-searches, which ingest outsider-authored content.

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

• Direct money access detected (medium risk: 0.30). The skill integrates with 拾流 (Shiliu) for creator research and content creation, with functionality mentioning source subscriptions, data calls, and quotes involving max_charge_cents (SKILL.md:40, SKILL.md:67). However, these represent service usage costs and indirect API billing or quote collection rather than direct fund transfers, charges, or settlement authorizations performed by the skill itself. Consequently, it falls under indirect operations with documented pricing checks.