ClawHub
Back to skill

Security audit

Invisible Work Illuminator

Security checks across malware telemetry and agentic risk

Overview

This is an instruction-only writing helper that rewrites behind-the-scenes work into achievement language and does not request access to files, accounts, credentials, or tools.

Safe to install as a writing-assistance skill. Review generated resume, performance review, or status-update language for accuracy, and ask for English or another language if the default Chinese structure is not what you need.

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 (1)

Natural-Language Policy Violations

Medium
Confidence
93% confidence
Finding
The skill hardcodes Chinese output structure and preferred verbs without offering a language choice, which can override the user's expected language and reduce transparency about how responses are generated. While not a classic security exploit, it is a prompt-safety and policy issue because it constrains output behavior in a way the user may not have requested, potentially causing misleading, unusable, or non-compliant responses in multilingual contexts.

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.