Security audit

smartchart

Security checks across malware telemetry and agentic risk

Overview

This is a straightforward SmartChart CLI helper whose main risk is sending query inputs through an external data platform.

Before installing, verify that the smartchart Python package and SmartChart service are the provider you intend to use. Avoid sending secrets, regulated data, internal identifiers, or confidential business parameters through SmartChart unless you trust its service and understand its data handling.

SkillSpector

By NVIDIA

Vulnerability Patterns

Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
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)

Lp3

Medium

Category: MCP Least Privilege
Confidence: 85% confidence
Finding: The skill instructs the agent to invoke a shell-accessible CLI (`smartchart`) but does not declare any permissions or constraints around shell execution. This creates a capability/expectation mismatch that can lead to unsafe tool use, reduced review visibility, and accidental execution of external commands in environments that treat undeclared shell access as restricted.

Vague Triggers

Medium

Confidence: 88% confidence
Finding: The trigger description is very broad and can activate on common requests such as querying data, listing tools, fetching metrics, or performing data retrieval tasks. Over-broad routing increases the chance this skill is invoked for unrelated requests, causing unnecessary shell/CLI access and data exposure that would not be needed for the user’s actual task.

VirusTotal

65/65 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.