ClawHub

Personal Ideas

Security checks across malware telemetry and agentic risk

Overview

This looks like a legitimate personal ideas notebook, but it may save private thoughts automatically and too broadly without clear user consent.

Install only if you are comfortable with the agent saving idea-like statements into a persistent local notes file. Treat it as a private notebook: avoid sharing secrets, credentials, or confidential plans unless you explicitly want them stored, and prefer asking the agent to confirm before saving or to delete stored ideas when no longer needed.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (3)

Vague Triggers

Medium
Confidence
91% confidence
Finding
The activation description includes very broad triggers like 'idea', 'thought', 'concept', 'project idea', and 'what if', which are common in ordinary conversation. This can cause the skill to activate unexpectedly in unrelated contexts, increasing the chance that personal content is processed or persisted without clear user intent.

Missing User Warnings

Medium
Confidence
96% confidence
Finding
The skill tells the agent to save newly mentioned ideas into a persistent file, but gives no requirement to notify the user or obtain consent before storing potentially sensitive personal or business information. In the context of a personal ideas notebook, users may share confidential startup plans, private reflections, or commercially sensitive concepts, making silent retention risky.

Missing User Warnings

Medium
Confidence
97% confidence
Finding
The rules say to record everything and store it in persistent memory, again without retention limits, sensitivity checks, or user-facing warning. This broad retention policy amplifies the danger of collecting sensitive data by default and makes accidental over-collection more likely.

VirusTotal

65/65 vendors flagged this skill as clean.

View on VirusTotal