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 sqlite3 CLI 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
Risk Level
SAFE
Analyzed
Jun 17, 2026, 09:10 AM
Security Audit — agent-trust-hub — huawei-cloud-ascend-profiler-db-explorer