ClawHub
Back to skill

Security audit

Newsletter & Creator Pack

Security checks across malware telemetry and agentic risk

Overview

This is a disclosed newsletter workflow helper with no executable code, though users should review outreach drafts and confirm any file saves.

Install if you want help creating newsletter assets, sponsor outreach drafts, reactivation sequences, or performance reports. Do not paste unnecessary subscriber personal data, review all outreach before sending, and only approve file writes after checking the exact destination and overwrite risk.

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 invocation guidance is broad enough to trigger on generic writing or marketing requests that are not clearly asking for this specific skill. That can cause the agent to inappropriately enter a workflow that performs outreach, analysis, or file-writing actions the user did not explicitly request, increasing the chance of unintended actions or privacy-impacting data handling.

Missing User Warnings

Medium
Confidence
94% confidence
Finding
The skill instructs saving outputs to a fixed filesystem path under the user's home directory, which creates a side effect on local storage and may expose data in a predictable location. Even though it says to confirm save location before writing, the default fixed path and directory creation behavior can still lead to unintended writes, overwrites, or storage of sensitive business content without sufficiently clear opt-in.

VirusTotal

65/65 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.