appwrite-kotlin
Pass
Audited by Gen Agent Trust Hub on Oct 23, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill exposes an attack surface for indirect prompt injection by facilitating the ingestion of external data from database rows, real-time subscriptions, and serverless function requests.
- Ingestion points: Data retrieved via
TablesDB.listRows,Realtime.subscribe, andRuntimeContextwithin serverless function handlers inSKILL.md. - Boundary markers: The skill does not provide specific instructions for the AI to wrap or delimit this untrusted external data.
- Capability inventory: The skill possesses write capabilities including file creation (
Storage.createFile), database modification (TablesDB.createRow), and function execution (Functions.createExecution). - Sanitization: No explicit input validation or sanitization mechanisms are defined in the provided code templates.
Audit Metadata