Security audit

Shopify Store Translator

Security checks across malware telemetry and agentic risk

Overview

The skill is mostly transparent, but it asks for Shopify market-write access and includes market creation/update guidance that is broader than its top-level translation-only framing.

Install only if you intend to let the agent use Shopify read/write access for translations, locales, and markets. Before any write, require a preview listing the exact resources, locales, markets, web presences, and full alternateLocales lists that will change; do not enable long-running credentials or the automation token unless you need unattended approved permission releases.

SkillSpector

By NVIDIA

Vulnerability Patterns

Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
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: 87% confidence
Finding: The document includes multiple state-changing mutations that enable locales, publish them, create markets, alter web presences, and replace alternate locale lists, but it does not consistently require explicit user confirmation immediately before destructive or configuration-changing actions. In an agent setting, this can lead to unintended storefront exposure, market routing changes, or accidental removal of existing locale settings if the agent acts on inferred intent.

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

Detected: suspicious.dangerous_exec, suspicious.env_credential_access, suspicious.exposed_secret_literal (+1 more)

Shell command execution detected (child_process).

Critical

Code: suspicious.dangerous_exec
Location: scripts/lib/shopify-cli.mjs:57

Environment variable access combined with network send.

Critical

Code: suspicious.env_credential_access
Location: scripts/lib/shopify-dev-dashboard-auth.mjs:4

File appears to expose a hardcoded API secret or token.

Critical

Code: suspicious.exposed_secret_literal
Location: references/onboarding-guide.md:45

Prompt-injection style instruction pattern detected.

Warn

Code: suspicious.prompt_injection_instructions
Location: SKILL.md:67