import
Pass
Audited by Gen Agent Trust Hub on Sep 18, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [SAFE]: The skill facilitates administrative tasks for Zilliz Cloud, such as importing data and managing storage stages. These operations are performed using the vendor's official 'zilliz' CLI.- [COMMAND_EXECUTION]: The skill utilizes the 'zilliz' CLI tool to perform resource management tasks including 'import start', 'import list', and 'stage create'. These are legitimate vendor-specific administrative commands.- [INDIRECT_PROMPT_INJECTION]: The skill processes data from external cloud storage, which represents a potential surface for indirect prompt injection. 1. Ingestion points: External data files (Parquet, JSON, CSV) referenced in the 'zilliz import start' command. 2. Boundary markers: Absent; the instructions do not specify delimiters to separate data from commands. 3. Capability inventory: Execution of 'zilliz' CLI commands for cloud resource management. 4. Sanitization: Absent; the skill does not explicitly include validation or sanitization steps for the imported data content.
Audit Metadata