Security Audit

openai/skills:skills/.curated/winui-app

github.com/openai/skills

AI SkillCommit 49f948faa925

TRUSTED

Scanned about 8 hours ago

Critical

Immediate action required

High

Priority fixes suggested

Medium

Best practices review

Low

Acknowledged / Tracked

Trust Assessment

openai/skills:skills/.curated/winui-app received a trust score of 85/100, placing it in the Mostly Trusted category. This skill has passed most security checks with only minor considerations noted.

SkillShield's automated analysis identified 1 finding: 0 critical, 1 high, 0 medium, and 0 low severity. Key findings include Arbitrary Command Execution via WinGet Configuration.

The analysis covered 4 layers: Manifest Analysis, Static Code Analysis, Dependency Graph, LLM Behavioral Safety. All layers scored 70 or above, reflecting consistent security practices.

Last analyzed on July 17, 2026 (commit 49f948fa). SkillShield performs automated 4-layer security analysis on AI skills and MCP servers.

Layer Breakdown

Manifest Analysis

100%

Static Code Analysis

100%

Dependency Graph

100%

LLM Behavioral Safety

85%

Behavioral Risk Signals

Filesystem Write

1 finding

Shell Execution

1 finding

Excessive Permissions

1 finding

Security Findings1

Severity	Finding	Layer	Location
HIGH	Arbitrary Command Execution via WinGet Configuration The skill instructions mandate running a local WinGet configuration file (`winget configure -f config.yaml --accept-configuration-agreements --disable-interactivity`) automatically during the setup/bootstrap flow. Because `config.yaml` is part of the workspace/repository and can be modified by untrusted inputs or PRs, this allows arbitrary system configuration changes, software installations, or script execution with elevated privileges on the user's machine without interactive confirmation. Avoid running WinGet configurations automatically with `--disable-interactivity`. Prompt the user with the specific changes to be made, or require manual execution and verification of the `config.yaml` contents before running the command.	LLM	SKILL.md:21

Scan History

Embed Code

[![SkillShield](https://skillshield.io/api/v1/badge/be87d47c3f884d57.svg)](https://skillshield.io/report/be87d47c3f884d57)