huawei-cloud-ascend-profiler-db-explorer
Pass
Audited by Gen Agent Trust Hub on Jun 17, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill utilizes the
sqlite3CLI and a local Python script (scripts/get_schema.py) to interact with profiling databases and extract metadata. - [PROMPT_INJECTION]: The skill processes external database files which constitutes an indirect injection surface. Mitigation is provided through instructions enforcing result limits (
LIMIT 20) and aggregation, reducing the risk of context flooding or unauthorized data extraction.
Audit Metadata