data-analysis-operation

• Outcome: Review
• Latest audit: Jun 3, 2026 · 8:08 AM UTC
• Version: 1.0.2

Overview

This data-analysis skill appears legitimate, but it needs review because running it can automatically install Python packages and produce transformed datasets without clear upfront user control.

Review before installing. Use it only in an isolated Python environment or disposable workspace, and expect it may install packages from the package index if dependencies are missing. Confirm output paths and keep original datasets backed up before using any cleaning workflow.

SkillSpector

By NVIDIA

Vulnerability Patterns

• Excessive Agency: Unrestricted Tool Access, Autonomous Decision Making, Scope Creep
• Trigger Abuse: Overly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
• Behavioral AST: exec() Call, eval() Call, Dynamic Import
• MCP Least Privilege: Underdeclared Capability, Wildcard Permission, Missing Permission Declaration
• MCP Tool Poisoning: Hidden Instructions, Unicode Deception, Parameter Description Injection

Findings (9)

subprocess module call

Medium

• Category: Dangerous Code Execution

Content

except ImportError:
    print("Required packages not found. Installing dependencies...")
    import subprocess
    subprocess.check_call([sys.executable, "-m", "pip", "install", "pandas", "openpyxl", "numpy", "-q"])
    import pandas as pd
    import numpy as np
    from openpyxl import Workbook

• Confidence: 97% confidence
• Finding: subprocess.check_call([sys.executable, "-m", "pip", "install", "pandas", "openpyxl", "numpy", "-q"])

subprocess module call

Medium

• Category: Dangerous Code Execution

Content

except ImportError:
    print("Required packages not found. Installing pandas and openpyxl...")
    import subprocess
    subprocess.check_call([sys.executable, "-m", "pip", "install", "pandas", "openpyxl", "-q"])
    import pandas as pd
    from openpyxl import Workbook
    from openpyxl.styles import Font, PatternFill, Alignment, Border, Side

• Confidence: 95% confidence
• Finding: subprocess.check_call([sys.executable, "-m", "pip", "install", "pandas", "openpyxl", "-q"])

Lp3

Medium

• Category: MCP Least Privilege
• Confidence: 91% confidence
• Finding: The skill advertises shell-based execution of local Python scripts but does not declare any permissions or trust boundaries. This can mislead users or orchestrators about the skill's actual capabilities, increasing the risk of unintended command execution, file access, and local data modification when the skill is invoked.

Context-Inappropriate Capability

Medium

• Confidence: 98% confidence
• Finding: Automatically installing Python packages is not required to analyze user-provided Excel/CSV files and introduces avoidable supply-chain and environment-modification risk. In an agent skill context, this is more dangerous because execution may occur on shared or privileged automation hosts where silent package installation can alter future runs or execute untrusted package installer code.

Context-Inappropriate Capability

Medium

• Confidence: 98% confidence
• Finding: Installing Python packages during normal execution is unjustified for a simple column-comparison utility and expands the trust boundary from local file processing to remote package retrieval. In an agent skill context, this is more dangerous because the skill may run unattended on user systems or shared runners, allowing environment mutation and potential supply-chain compromise.

Missing User Warnings

Medium

• Confidence: 88% confidence
• Finding: The skill describes automatic data cleaning and report generation without clearly warning that these actions can alter datasets or create new files. In a data-processing context, hidden write or modification behavior can cause accidental data loss, overwrite important files, or expose sensitive data in generated reports.

Missing User Warnings

Medium

• Confidence: 98% confidence
• Finding: The script silently installs dependencies without prior notice or consent, causing unexpected outbound network access and code execution during what appears to be a local analysis task. That mismatch between stated purpose and actual behavior is a security concern because users and operators may run it in restricted environments assuming it is read/process-only.

Missing User Warnings

Medium

• Confidence: 97% confidence
• Finding: The script installs packages automatically without prior confirmation, so simply running a data-analysis tool can trigger network access and code installation on the host. This violates least surprise and can be abused in restricted or sensitive environments where unapproved package installation creates security, compliance, and reliability risks.

Missing User Warnings

Medium

• Confidence: 91% confidence
• Finding: The clean_data function removes empty columns and duplicate rows, modifies missing values, and strips string fields before writing the transformed dataset out, but it does not provide an explicit confirmation step, preview/dry-run mode, or clear warning that records may be permanently omitted from the produced output. In a data-processing skill, this can cause silent data loss, integrity issues, or accidental misuse when users treat the cleaned file as authoritative without understanding what was removed or altered.

VirusTotal

63/63 vendors flagged this skill as clean.

Static analysis

No suspicious patterns detected.