REPORT 01M7BWE1F22V4HSPJG12SANQYZ · checks-v2
comment-code-generate-a-tutorial skill: automated checks
What HostedMCP checked on 14 Nov 2026, 01:58 UTC in github/awesome-copilot/skills/comment-code-generate-a-tutorial on the default branch. Every result links to the public source it came from, so you can check it yourself.
Passed HostedMCP checks v2
100/100
6 of 6 checks ran · 0 high findings · not a security audit
- Checked
- 14 Nov 2026, 01:58 UTC
- Files read
- SKILL.md and scripts
- Methodology
- checks-v2
Origin
35 / 35 points- 合格ソースリポジトリがリンクされており、アクセス可能15 pts
github/awesome-copilot/skills/comment-code-generate-a-tutorial is public and reachable
github.com/github/awesome-copilot/tree/HEAD/skills/comment-code-genera ↗ - 合格
- 合格
Scripts
30 / 30 points- 合格スクリプトにダウンロード実行や認証情報の窃取がない30 pts
No scripts in the skill folder
Instructions to the agent
35 / 35 points- 合格SKILL.md に隠れた指示がない25 pts
No override phrases, safeguard switches, credential requests or hidden characters
github.com/github/awesome-copilot/blob/HEAD/skills/comment-code-genera ↗ - 合格事前許可ツールが限定されている10 pts
No pre-approved tools; the agent asks before using one
github.com/github/awesome-copilot/blob/HEAD/skills/comment-code-genera ↗
What these checks do not cover
- Scripts are read, never run. Their logic is not audited, and up to five scripts per skill are read.
- Results describe github/awesome-copilot/skills/comment-code-generate-a-tutorial on the date above; a later commit can differ.
- A pass is not a guarantee of safety. Read the scripts before you let an agent run them, and keep allowed-tools narrow.