Transmission

Security checks across malware telemetry and agentic risk

Overview

The skill is a coherent transmission CAD workflow that uses a disclosed external service, but users should treat submitted design parameters and generated guest links as potentially sensitive.

Install only if you are comfortable sending transmission design inputs to jixietools.com and receiving a guest-accessible production sheet link. Avoid using confidential or proprietary designs unless you trust that service's handling and retention of the data.

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: 87% confidence
Finding: The trigger phrases include very generic terms such as “变速器” and “transmission”, which can match ordinary conversation and invoke the skill unexpectedly. Because the skill then drives users into an external workflow that collects technical data and submits it to third-party APIs, accidental activation increases the chance of unintended data disclosure or unauthorized external actions.

Missing User Warnings

Medium

Confidence: 96% confidence
Finding: The skill instructs the agent to collect detailed engineering parameters and send them to an external service, then create and monitor a production sheet without authentication, but it provides no user-facing disclosure or consent step. This is dangerous because users may unknowingly transmit proprietary design inputs and create externally accessible artifacts tied only to a guest code.

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal