Back to skill

Security audit

技能安全扫描(免费版)

Security checks across malware telemetry and agentic risk

Overview

The skill appears to be a security-scanner wrapper, but it asks for broader local authority than its documented workflow needs and under-explains what data is sent to the external scanner service.

Review this skill before installing. It is not clearly malicious, but it grants local read/exec/write capability for a workflow that mostly appears to call an external API. Avoid using confidential internal skill names or callback URLs unless you are comfortable sending them to the scanner service, and prefer a version that removes or scopes write access and documents external data handling.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
  • 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)

Context-Inappropriate Capability

Medium
Confidence
94% confidence
Finding
The skill requests write capability even though its stated purpose is only to query an external scanner and return a report. Unnecessary write permission violates least privilege and could allow unintended file modification, persistence, or tampering if the skill logic is later extended or abused.

Missing User Warnings

Medium
Confidence
89% confidence
Finding
The skill sends skill identifiers and possibly callback URLs to an external Scanner API, but the documentation does not warn users that this information leaves the local environment. This can lead to unintentional disclosure of internal project names, ownership metadata, or network endpoints to a third party.

VirusTotal

VirusTotal findings are pending for this skill version.

View on VirusTotal

Static analysis

No suspicious patterns detected.