Security audit

QC Data Processor

Security checks across malware telemetry and agentic risk

Overview

This skill is a disclosed QC data analysis MCP server, with no evidence of hidden exfiltration or destructive behavior, but it should only be used with trusted local data files and controlled dependencies.

Install only in an environment where the MCP server can access the QC files you intend to analyze. Avoid pointing it at sensitive unrelated files, and prefer pinning or locking dependencies to reviewed versions before production use.

SkillSpector

By NVIDIA

Vulnerability Patterns

Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
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

Findings (9)

Vague Triggers

Medium

Confidence: 87% confidence
Finding: The trigger keyword list includes broad, common terms such as "日报", "周报", and "客诉", which can match routine business conversations unrelated to SPC or reliability analysis. This increases the chance of unintended skill activation, causing the agent to route user requests to this skill inappropriately and potentially expose local file-processing behavior or produce misleading analysis in the wrong context.

Missing User Warnings

Low

Confidence: 93% confidence
Finding: The function trusts `_file_path` from `data_schema` and directly opens it with `pd.read_csv`/`pd.read_excel` without validation, restriction, or user disclosure. In an MCP/server context, this can become arbitrary local file read, allowing a caller to access unintended files on the host if they can influence `data_schema`.

Unpinned Dependencies

Low

Category: Supply Chain
Content: mcp>=1.0.0 pandas>=2.0.0 openpyxl>=3.0.0 numpy>=1.24.0
Confidence: 90% confidence
Finding: mcp>=1.0.0

Unpinned Dependencies

Low

Category: Supply Chain
Content: mcp>=1.0.0 pandas>=2.0.0 openpyxl>=3.0.0 numpy>=1.24.0 scipy>=1.10.0
Confidence: 87% confidence
Finding: pandas>=2.0.0

Unpinned Dependencies

Low

Category: Supply Chain
Content: mcp>=1.0.0 pandas>=2.0.0 openpyxl>=3.0.0 numpy>=1.24.0 scipy>=1.10.0 reliability>=0.8.0
Confidence: 87% confidence
Finding: openpyxl>=3.0.0

Unpinned Dependencies

Low

Category: Supply Chain
Content: mcp>=1.0.0 pandas>=2.0.0 openpyxl>=3.0.0 numpy>=1.24.0 scipy>=1.10.0 reliability>=0.8.0
Confidence: 86% confidence
Finding: numpy>=1.24.0

Unpinned Dependencies

Low

Category: Supply Chain
Content: pandas>=2.0.0 openpyxl>=3.0.0 numpy>=1.24.0 scipy>=1.10.0 reliability>=0.8.0
Confidence: 86% confidence
Finding: scipy>=1.10.0

Unpinned Dependencies

Low

Category: Supply Chain
Content: openpyxl>=3.0.0 numpy>=1.24.0 scipy>=1.10.0 reliability>=0.8.0
Confidence: 86% confidence
Finding: reliability>=0.8.0

Known Vulnerable Dependency: mcp==1.0.0 — 3 advisory(ies): CVE-2025-53366 (MCP Python SDK vulnerability in the FastMCP Server causes validation error, lead); CVE-2025-66416 (Model Context Protocol (MCP) Python SDK does not enable DNS rebinding protection); CVE-2025-53365 (MCP Python SDK has Unhandled Exception in Streamable HTTP Transport, Leading to )

High

Category: Supply Chain
Confidence: 98% confidence
Finding: mcp==1.0.0

VirusTotal

58/58 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.