Uberduck

Security checks across malware telemetry and agentic risk

Overview

This skill is a disclosed Uberduck integration using Membrane for authenticated API access, with normal external-service privacy and account-action risks but no hidden or malicious behavior found.

Install this only if you are comfortable letting Membrane broker authenticated Uberduck requests. Review any action or proxy request that uploads text, voice-related content, creates resources, changes account data, or deletes data; in controlled environments, consider pinning the Membrane CLI version instead of using latest.

SkillSpector

By NVIDIA

Vulnerability Patterns

Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code

Findings (2)

Vague Triggers

Medium

Confidence: 92% confidence
Finding: The skill description is broad enough that an agent may invoke it for generic 'manage data' or workflow requests that are not clearly Uberduck-specific. That can cause unintended routing of user tasks into an external integration, increasing the chance of unnecessary data exposure or unauthorized actions against a connected third-party service.

Missing User Warnings

Medium

Confidence: 89% confidence
Finding: The documentation encourages direct proxied API requests to Uberduck without telling the agent to warn the user that prompts, text, or other data will be transmitted to a third-party service. In a TTS/voice platform context, submitted content may be sensitive, copyrighted, or privacy-impacting, so silent transmission creates meaningful confidentiality and consent risks.

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal