huawei-cloud-mrs-clickhouse-sql-check
Fail
Audited by Gen Agent Trust Hub on Jul 30, 2026
Risk Level: HIGHCOMMAND_EXECUTION
Full Analysis
- [COMMAND_EXECUTION]: Workflow instructions in
SKILL.md(Steps 2-5) provide shell command templates that incorporate raw user-provided SQL text within double quotes, such aspython ... "<sql_text>". This creates a critical command injection vulnerability. If a user provides input containing shell operators like;,&, or backticks, they can execute arbitrary system commands on the host machine. - [COMMAND_EXECUTION]: The
scripts/version_loader.pyscript usesimportlib.utilto dynamically load Python modules from paths constructed using a user-specified version parameter. While the skill attempts to validate this parameter against a list of local directories, dynamic code execution from computed paths remains a significant security risk.
Recommendations
- AI detected serious security threats
Audit Metadata