skill-creator
Pass
Audited by Gen Agent Trust Hub on Feb 27, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The
eval-viewer/viewer.htmlcomponent loads the SheetJS library (xlsx.full.min.js) fromcdn.sheetjs.comand typography assets fromfonts.googleapis.com. These are well-known technology providers used for the skill's evaluation visualization features. - [COMMAND_EXECUTION]: The
scripts/run_eval.pyscript usessubprocess.Popento execute theclaudeCLI. This allows the skill to programmatically verify triggering behavior by simulating user queries against a temporary skill configuration. - [COMMAND_EXECUTION]: The
eval-viewer/generate_review.pyscript invokeslsofviasubprocess.runto detect and terminate any existing processes bound to the target port (3117). This is a routine operation to ensure the local feedback server can initialize without conflicts. - [COMMAND_EXECUTION]: The skill utilizes several internal Python scripts (
aggregate_benchmark.py,package_skill.py) to manage data processing and skill distribution, which are executed via the command line as part of the intended workflow.
Audit Metadata