technical-blog-writing
Pass
Audited by Gen Agent Trust Hub on Sep 8, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTIONDYNAMIC_EXECUTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill references installation guidelines hosted on GitHub (
raw.githubusercontent.com), which is a well-known service. - [COMMAND_EXECUTION]: Utilizes
npxand a custombeltCLI tool to manage skill installations and execute application logic. - [DYNAMIC_EXECUTION]: Generates and runs Python code snippets (using
matplotlib) through an executor tool to create visual charts from data based on provided templates. - [INDIRECT_PROMPT_INJECTION]: The skill ingests data from external web searches via the
exa/searchtool, which presents an attack surface for instructions embedded in third-party content.
Audit Metadata