Book a 30-minute demo →
Skill scan report

github-copilot-upgrader

View on GitHub
35 Medium Automated analysis flagged 2 potential risk patterns.

What this skill does

The skill is designed to upgrade the @github/copilot npm package in the vscode-copilot-chat project. It provides a step-by-step process for upgrading the package, including creating a TODO list, snaps

github/microsoft - Command Injection - 188.5k stars

ThreatsCommand Injection Insecure Process

Threat analysis

Command Injection1 finding
Insecure Process1 finding

Skill info

Namemicrosoft/github-copilot-upgrader
Registrygithub
Versionc886ff4
PURLpkg:github/microsoft/vscode@c886ff4?skill=github-copilot-upgrader
Stars188.5k

Assessments (2)

Command Injection1 finding HIGH
HIGH

Command Injection via local-llm-review

SKILL.md

The skill instructs the user to run `npm install @github/copilot@latest` followed by `npm run postinstall` without validating or sanitizing the commands. This could be exploited if the package name or
Insecure Process1 finding MEDIUM
MEDIUM

Insecure Process via local-llm-review

SKILL.md

The skill instructs the user to run `npm run postinstall` without any checks or safeguards. This could execute arbitrary code if the postinstall script is malicious.

Badge

Add the Anomity scan badge for github-copilot-upgrader to your README.

Anomity Skill Check badge

Markdown
[![Anomity Skill Check](https://anomity.ai/skills/badge.svg)](https://anomity.ai/skills/github/microsoft/github-copilot-upgrader/)
HTML
<a href="https://anomity.ai/skills/github/microsoft/github-copilot-upgrader/"><img src="https://anomity.ai/skills/badge.svg" alt="Anomity Skill Check"></a>
Image URL
https://anomity.ai/skills/badge.svg

How Anomity governs this at runtime

Scan-time vetting tells you what a skill says it will do. Anomity's Endpoint Sensor sees what agents actually do: it discovers skills alongside every other AI artifact on the endpoint, and runtime governance can allow, deny, or log the tool calls a skill triggers. Policy violations route to your SIEM, Slack, email, or Jira, backed by a queryable 90-day audit trail.

Book a 30-minute demo to see your own skill inventory.

Methodology and disputes

Every skill is assessed by the Anomity Skill Intelligence engine against its public source; findings indicate risk patterns, not confirmed exploitation. Maintainer of github-copilot-upgrader? Report an issue or request a rescan.

Ask AI about Anomity
ChatGPT Claude Perplexity Google AI Grok