Is @azure/mcp-win32-x64 safe?

No malicious indicators - review capabilities before installing

Notable — review in context (capabilities are not malware):

Node.js shell/command execution

@azure/mcp-win32-x64 is an AI npm_package analyzed by SkillTotal's deterministic static scanner. The scan found no malicious indicators, though 1 risky construct are reported for review. It can: shell execution — capabilities are what the code can do, not a verdict on intent. Risk score 0/100 (low).

@azure/mcp-win32-x64 3.0.0-beta.48

npm_package · npm:@azure/mcp-win32-x64

LOW

/ 100 risk score

Snapshot · scanned Sep 30, 2026 · @azure/mcp-win32-x64@3.0.0-beta.48 · engine 0.53.0 / ruleset 60

Automated static-analysis result. It can contain false positives and false negatives, and is not a claim about the intent of @azure/mcp-win32-x64's authors. Report a false positive.

Capabilities — what this component can do (not a risk score):

shell execution

Behavioral traits

How this component maps to the CSA agentic threat model. Descriptive — it never affects the risk score.

Execution authority

Tool Access Control / Direct Tool Access

Findings (1)

HIGHNode.js shell/command executionST-SHELL-NODE

The component can run operating-system commands or spawn processes.

index.js:5-5

const childProcess = require('child_process')

index.js:48-48

const child = childProcess.spawn(execPath, args, {

Why it matters: Powerful and often legitimate — confirm the commands aren't built from untrusted input.

Fix: Confirm the command and its arguments are fully controlled and not derived from untrusted input; prefer execFile with an argument array.

Check your own component

Run the same evidence-backed scan on any MCP server, agent skill, or package.

Scan your own component

How we determine this: deterministic static analysis (regex + AST), evidence-anchored, no code execution. Methodology →