CSV Wizard

Security checks across malware telemetry and agentic risk

Overview

This appears to be a normal data-cleaning skill, with the main risk being that some cleaning options can remove or overwrite data if used carelessly.

Install only if you are comfortable with a tool that can remove rows, change values, and write cleaned datasets. Keep original data backed up, prefer writing to a new output file, and review which cleaning options are lossy before running them on important files.

SkillSpector

By NVIDIA

Vulnerability Patterns

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
Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep

Findings (2)

Missing User Warnings

Medium

Confidence: 87% confidence
Finding: The README promotes destructive cleaning actions such as dropping rows with missing values and removing duplicates, but it does not clearly warn users that these operations can irreversibly alter datasets or discard records. In a data-cleaning CLI, this can lead to accidental data loss, especially when users copy examples directly or run commands on important files without understanding the consequences.

Missing User Warnings

Medium

Confidence: 88% confidence
Finding: The skill explicitly supports destructive cleaning operations such as dropping rows with missing values, removing duplicates, and writing transformed output, but it does not warn users that these actions can irreversibly alter datasets or cause silent data loss if the output path overwrites an existing file. In a data-cleaning CLI, this is a genuine safety issue because users may run examples verbatim and unintentionally destroy or degrade valuable data.

VirusTotal

60/60 vendors flagged this skill as clean.

View on VirusTotal