majia-siyu
Pass
Audited by Gen Agent Trust Hub on Nov 2, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
- [COMMAND_EXECUTION]: The skill invokes various shell commands for updating, linting, and planning. It uses git and npx for version management and relies on a local siyu-plan CLI tool and various Python scripts (e.g., qunfa_lint.py) for copy validation.
- [INDIRECT_PROMPT_INJECTION]: The skill ingests untrusted data from user inputs and external research. It proactively addresses this risk through explicit architectural rules that label ingested data as untrusted and require human approval before proceeding with multi-agent orchestration steps.
- [EXTERNAL_DOWNLOADS]: The update functionality fetches code updates from the author's official GitHub repository (maojiebc/majia-siyu-team) using standard package management tools.
Audit Metadata