REPORT 01M7BT4SMNVKBQ2AV9QNX4Q6MH · checks-v2
debugview skill: automated checks
What HostedMCP checked on 14 Nov 2026, 01:18 UTC in microsoft/skills/.github/skills/debugview 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, 01:18 UTC
- Files read
- SKILL.md and scripts
- Methodology
- checks-v2
Origin
35 / 35 points- LolosSource repository terhubung dan dapat dijangkau15 pts
microsoft/skills/.github/skills/debugview is public and reachable
github.com/microsoft/skills/tree/HEAD/.github/skills/debugview ↗ - Lolos
- LolosAda commit atau release dalam satu tahun terakhir10 pts
Last commit 2026-11-11
github.com/microsoft/skills/commits ↗
Scripts
30 / 30 points- LolosSkrip tanpa unduh-lalu-jalankan atau pencurian kredensial30 pts
3 scripts read; no download-and-run, remote eval, base64 execution or credential upload
Instructions to the agent
35 / 35 points- LolosTidak ada instruksi tersembunyi di SKILL.md25 pts
No override phrases, safeguard switches, credential requests or hidden characters
github.com/microsoft/skills/blob/HEAD/.github/skills/debugview/SKILL.m ↗ - LolosTool yang diizinkan otomatis dibatasi10 pts
No pre-approved tools; the agent asks before using one
github.com/microsoft/skills/blob/HEAD/.github/skills/debugview/SKILL.m ↗
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 microsoft/skills/.github/skills/debugview 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.