Deepl

Security checks across malware telemetry and agentic risk

Overview

This is a disclosed DeepL integration through Membrane, with normal account-access and glossary-management risks but no evidence of hidden or malicious behavior.

Install only if you trust Membrane and intend to connect the selected DeepL account. Review any create or delete glossary action carefully, prefer named actions over raw proxy requests, and revoke the Membrane connection when it is no longer needed.

SkillSpector

By NVIDIA

Vulnerability Patterns

Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access

Findings (2)

Vague Triggers

Medium

Confidence: 91% confidence
Finding: The manifest description says to use the skill whenever the user wants to interact with DeepL data, which is a broad activation cue that can cause the agent to invoke this skill in situations where user intent is ambiguous. Overly broad routing increases the chance of unintended external actions, account access, or data handling without sufficiently explicit user direction.

Missing User Warnings

Medium

Confidence: 88% confidence
Finding: The documentation exposes a destructive capability, 'Delete Glossary', but provides no warning, confirmation, or recovery guidance. In an agent setting, that omission can lead to accidental deletion of user data if the model chooses the action based on a loosely phrased request or mistaken intent.

VirusTotal

63/63 vendors flagged this skill as clean.

View on VirusTotal