huawei-cloud-mrs-hive-sql-check

Warn

Audited by Gen Agent Trust Hub on Jul 22, 2026

Risk Level: MEDIUMCOMMAND_EXECUTION
Full Analysis
  • [COMMAND_EXECUTION]: The instructions in SKILL.md recommend that the agent execute local Python scripts by interpolating raw user input into a shell command: python ~/.cac/skills/huawei-cloud-mrs-hive-sql-check/scripts/hive_sql_checker.py "<sql_text>" all. Because the user-controlled <sql_text> is placed directly inside a double-quoted string within a shell command, an attacker can escape the quotes using shell metacharacters (e.g., ;, &, |, `) to execute arbitrary commands on the host system.
  • [SAFE]: The underlying Python scripts (hive_sql_checker.py, hive_sql_parser.py, hive_sql_tokenizer.py) perform static SQL analysis only. They do not import network-capable libraries like requests or urllib, and they do not attempt to connect to external databases or services.
  • [SAFE]: No hardcoded credentials, API keys, or secrets were found within the skill's scripts or configuration files. The tool is designed for offline validation.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Jul 22, 2026, 06:45 PM
Security Audit — agent-trust-hub — huawei-cloud-mrs-hive-sql-check