Security audit

Zaira Tool Research

Security checks across malware telemetry and agentic risk

Overview

This skill is a disclosed read-only research connector to Zaira Labs, with a clear but manageable supply-chain and data-sharing consideration from its npm bridge.

Before installing, understand that searches and comparison prompts sent through this skill go to Zaira Labs, so avoid secrets, private source code, personal data, and sensitive customer details. The npm bridge is pinned by version and disclosed, but users with stricter supply-chain requirements may prefer a vendored or locally installed bridge.

SkillSpector

By NVIDIA

Vulnerability Patterns

Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep

Findings (1)

Missing User Warnings

Medium

Confidence: 92% confidence
Finding: This bridge implicitly downloads/executes an external npm package via `npx` and immediately connects it to a remote MCP endpoint, while piping local stdin/stdout through the spawned process. That creates a supply-chain and data-exfiltration boundary crossing without explicit user consent, version integrity verification, or local vendoring, so a compromised package, registry response, or remote service could process sensitive prompts and tool traffic.

VirusTotal

63/63 vendors flagged this plugin as clean.

View on VirusTotal

Static analysis

Detected: suspicious.dangerous_exec

Shell command execution detected (child_process).

Critical

Code: suspicious.dangerous_exec
Location: bin/zaira-guide-bridge.cjs:61
Evidence: const child = spawn(