zj-tech-design-review
Pass
Audited by Gen Agent Trust Hub on Sep 4, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill implements a framework for technical design reviews with an emphasis on verification and security.
- [COMMAND_EXECUTION]: The skill includes a Python script
scripts/validate_review.pyused to validate the structure of markdown documents. This script performs regex-based text analysis and does not execute arbitrary shell commands or access sensitive system resources. - [REMOTE_CODE_EXECUTION]: No remote code execution patterns were detected. The skill requires a local Python script for validation but does not download external scripts for execution.
- [DATA_EXFILTRATION]: No network operations or sensitive data access patterns were found. The skill operates entirely on local markdown files.
- [INDIRECT_PROMPT_INJECTION]: The skill defines a clear ingestion surface (markdown design documents) but includes explicit instructions to label assumptions and use deterministic quality gates, reducing the risk of the model blindly following instructions embedded in design text.
Audit Metadata