Security audit

azure-devops-tool-free

Security checks across malware telemetry and agentic risk

Overview

This skill mostly matches Azure DevOps use, but it gives PAT-backed command authority while making misleading local-only privacy claims and using overbroad activation guidance.

Review before installing. Use only a least-privilege Azure DevOps PAT, avoid running broad environment-variable checks, and require explicit confirmation before any PR creation. The publisher should correct the local-only privacy claim and narrow the trigger conditions to Azure DevOps tasks.

SkillSpector

By NVIDIA

Vulnerability Patterns

Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access

Findings (5)

Description-Behavior Mismatch

Medium

Confidence: 90% confidence
Finding: The skill advertises only five Azure DevOps core capabilities, but also instructs the agent to enumerate environment variables matching API/key/token/secret patterns and to run generic diagnostics. That expands behavior beyond the declared scope and can expose sensitive credential metadata or normalize broader shell access than users expect.

Description-Behavior Mismatch

Medium

Confidence: 97% confidence
Finding: The file claims data is kept local and not uploaded to the cloud, yet the skill explicitly depends on Azure DevOps API calls over the network. This is a misleading security claim that can cause users to disclose repository and project data under false assumptions about data handling.

Intent-Code Divergence

High

Confidence: 98% confidence
Finding: The FAQ explicitly states that all data remains local and is not uploaded to the cloud, directly contradicting the documented remote Azure DevOps REST usage. False assurances about privacy and locality are dangerous because they undermine informed consent and can lead users to expose sensitive organizational data or credentials to external services.

Vague Triggers

High

Confidence: 83% confidence
Finding: The trigger condition says to use the skill for broad data analysis, report generation, statistical insights, and visualization, which is inconsistent with the stated Azure DevOps project/repo/PR scope. Overbroad activation criteria can cause the agent to invoke this skill in unrelated contexts, increasing chances of unnecessary command execution or external API use.

Missing User Warnings

Medium

Confidence: 88% confidence
Finding: The skill includes PAT-authenticated curl examples that send requests to Azure DevOps but does not clearly warn users that project data, repository identifiers, branch names, PR content, and token-backed actions will be transmitted to an external service. In a skill with exec capability, that omission weakens informed consent and increases the risk of accidental sensitive-data exposure.

VirusTotal

VirusTotal findings are pending for this skill version.

View on VirusTotal

Static analysis

No suspicious patterns detected.