ClawHub
Back to skill

Security audit

Skill Interview Builder

Security checks across malware telemetry and agentic risk

Overview

This skill guides a user through creating and packaging a new Skill, and its file-writing behavior matches that purpose.

Before using it, confirm where the zip or folder will be written and review the file list. Do not upload credentials, private keys, sensitive personal data, or proprietary documents unless those files are meant to become part of the generated Skill package.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • 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
93% confidence
Finding
The skill explicitly instructs creating directories and writing files into the filesystem as part of its normal workflow, but it does not require obtaining explicit user confirmation immediately before performing those actions or warn that content will be persisted locally. In an agent setting, this can cause unintended writes, placement of user-supplied files into sensitive locations, or persistence of sensitive material that the user did not expect to be stored.

Missing User Warnings

Medium
Confidence
95% confidence
Finding
The delivery section directs the agent to package the generated skill as a zip, write files into a specified folder, or otherwise persist outputs, but it does not include a mandatory disclosure that archives and saved folders retain user content and uploaded materials. This is risky because users may provide sensitive documents during the interview flow, and those materials could be silently copied into archives or long-lived directories.

VirusTotal

65/65 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.