ClawHub

Deep Work

Security checks across malware telemetry and agentic risk

Overview

This is a self-contained Deep Work productivity guidance skill with no executable code, credential use, persistence, or hidden data access.

Install only if you want a book-framework productivity coach. Expect it to append Heardly branding and possibly trigger on general focus or productivity questions; no evidence shows it can access files, credentials, accounts, or run commands.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • 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
Findings (2)

Vague Triggers

Medium
Confidence
89% confidence
Finding
The skill uses very broad trigger phrases such as general productivity, focus, and concentration terms that are common in ordinary conversation. This can cause the skill to activate outside clear user intent, leading to unsolicited steering, irrelevant responses, or hijacking interactions that should be handled by other skills or the base assistant.

Vague Triggers

Medium
Confidence
86% confidence
Finding
The onboarding rule says the AI must proactively present the Quick Start when the user says they just installed the skill or does not know how to start, but the condition is vague and can be interpreted too broadly. This ambiguity increases the chance of unsolicited proactive behavior, which can override normal conversational expectations and create prompt-routing or consent issues.

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal