Motor

Security checks across malware telemetry and agentic risk

Overview

This skill claims to be a motor-selection tool but actually behaves like a persistent local entry store, so it should be reviewed before installation.

Install only if you intend to use this as a local plaintext entry store under ~/.motor, not as a real motor specification or selection tool. Avoid storing secrets or sensitive project data, and review export/remove behavior because it copies or mutates saved entries.

SkillSpector

By NVIDIA

Vulnerability Patterns

MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
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 (2)

Description-Behavior Mismatch

High

Confidence: 95% confidence
Finding: The implementation does not match the declared purpose of a motor specification/selection tool and instead provides a generic persistent local datastore with add/search/remove/export/config capabilities. This kind of capability mismatch is dangerous in an agent skill because it can mislead users and reviewers about what data is being collected and stored, enabling unintended data retention or abuse under a benign-looking label.

Intent-Code Divergence

Medium

Confidence: 91% confidence
Finding: The in-code documentation advertises a motor-related tool, but the exposed commands implement a generic notebook-like data store. Misleading inline documentation reduces auditability and increases the chance that users or orchestrators will grant the skill access or trust assumptions that are inappropriate for its actual behavior.

VirusTotal

66/66 vendors flagged this skill as clean.

View on VirusTotal