ClawHub
Back to skill

Security audit

csv-free

Security checks across malware telemetry and agentic risk

Overview

This CSV skill is not overtly malicious, but it needs review because it requests broad command/file authority and defines a callback URL without clear limits.

Review this skill before installing. It appears to be a basic CSV helper with no embedded executable code, but only use it with non-sensitive CSV data unless you understand whether callbacks are disabled or where they send data, and avoid granting command execution unless the publisher narrows or explains why it is needed.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Behavioral ASTexec() Call, eval() Call, Dynamic Import
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (2)

Missing User Warnings

Medium
Confidence
91% confidence
Finding
The skill declares `exec` and `write` tool capabilities but does not clearly warn users that it may execute commands or modify files. In an agent environment, that omission can mislead users into providing untrusted input or approving use of the skill without understanding that it has side effects beyond pure CSV formatting.

Missing User Warnings

Medium
Confidence
94% confidence
Finding
The skill advertises a `callback_url` parameter for asynchronous completion but does not warn that this may trigger outbound network communication and data transfer to a remote endpoint. Because CSV content can include sensitive business or personal data, undocumented callback behavior increases the risk of unintended exfiltration or privacy violations.

VirusTotal

VirusTotal findings are pending for this skill version.

View on VirusTotal

Static analysis

No suspicious patterns detected.