Translatecom

Security checks across malware telemetry and agentic risk

Overview

This appears to be a legitimate Translate.com integration, but it gives an agent broad authenticated API access without clear confirmation rules for changing data.

Review before installing if the connected Translate.com account contains confidential or business-critical data. Prefer discovered Membrane actions over raw proxy requests, only connect accounts you intend the agent to use, and require explicit confirmation before creating, modifying, deleting, or submitting sensitive translation content.

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: 84% confidence
Finding: The skill explicitly documents direct proxy requests with mutating HTTP methods like POST, PUT, PATCH, and DELETE, but it does not instruct the agent to confirm with the user before performing state-changing operations. In an agentic context, this can lead to unintended creation, modification, or deletion of Translate.com resources if the model infers a destructive action from ambiguous user input.

VirusTotal

65/65 vendors flagged this skill as clean.

View on VirusTotal