uniapp-cloud
Pass
Audited by Gen Agent Trust Hub on Oct 8, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [SAFE]: The skill consists entirely of markdown documentation, configuration guides, and code snippets for the uniCloud platform. All external references point to the official DCloud documentation domain (doc.dcloud.net.cn), which is a well-known service provider for uni-app developers.
- [INDIRECT_PROMPT_INJECTION]: The skill documents methods for ingesting and processing external data via cloud databases and functions, which creates a potential surface for indirect prompt injection. The skill mitigates this by providing specific guides on security rules and permissions.
- Ingestion points:
examples/database/crud.mdandapi/cloud-api.mddescribe adding data to collections. - Boundary markers: Absent in the provided code snippets.
- Capability inventory: The skill enables database CRUD operations, cloud storage management, and cloud function execution as part of its primary purpose.
- Sanitization: The snippets do not include explicit input sanitization, but the skill refers users to official DCloud security documentation for production implementation.
Audit Metadata