DeepL

Security checks across malware telemetry and agentic risk

Overview

This DeepL skill is a straightforward OOMOL connector wrapper for translation, language listing, and usage lookup, with no evidence of hidden or destructive behavior.

Install this only if you are comfortable sending translation text and usage requests through OOMOL's DeepL connector. Review the payload before translating sensitive text, and only run the one-time CLI install or login steps when you intentionally want to connect OOMOL and DeepL.

SkillSpector

By NVIDIA

Vulnerability Patterns

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
Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code

Findings (1)

Vague Triggers

Medium

Confidence: 85% confidence
Finding: The manifest says to use this skill for 'ANY DeepL request,' which is an overly broad routing instruction that can cause an agent to invoke the skill in situations beyond its narrowly documented capabilities. In an agentic system, broad trigger text increases the chance of unintended tool use, unnecessary transmission of user content to a third-party service, or misuse when a direct answer would suffice.

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal