tw-edu-research-viz
Pass
Audited by Gen Agent Trust Hub on May 4, 2026
Risk Level: SAFE
Full Analysis
- [COMMAND_EXECUTION]: The skill uses the Bash tool to execute local Python scripts (
scripts/generate_prisma.pyandscripts/generate_framework.py). These scripts are used to process user-provided research parameters and generate image files (PNG/SVG). - [DATA_EXFILTRATION]: No network operations or data exfiltration patterns were identified. All data processing occurs within the agent's environment, and outputs are saved to local directories.
- [PROMPT_INJECTION]: The instructions do not contain any attempts to override system prompts, bypass safety filters, or extract sensitive instructions.
- [DYNAMIC_EXECUTION]: The skill leverages standard Python libraries such as
matplotlibfor generating charts andpython-docxfor formatting documents. This is a standard and safe implementation for the skill's intended purpose.
Audit Metadata