ClawHub
Back to skill

Security audit

Creator Alpha Feed Free

Security checks across malware telemetry and agentic risk

Overview

This skill is a straightforward X content collection helper that writes a local Obsidian report, with some disclosure gaps users should notice before use.

Before installing, confirm the Obsidian Vault path and configuration file are correct, expect local Markdown files to be created, and avoid using callback_url unless you explicitly trust the destination. If using X, run it from a browser/session you are comfortable letting the agent read for AI-content collection.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • Behavioral ASTexec() Call, eval() Call, Dynamic Import
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Findings (3)

Vague Triggers

Medium
Confidence
86% confidence
Finding
The trigger phrase is broad enough that a generic request like collecting today's AI content could activate read/write/exec-capable behavior without an explicit confirmation boundary. In this skill's context, that is more dangerous because the skill can modify local files and potentially invoke execution flows tied to content collection.

Missing User Warnings

Medium
Confidence
93% confidence
Finding
The skill states it will write Markdown reports into an Obsidian Vault but does not clearly warn that it performs filesystem modifications. That can lead users to invoke the skill without realizing it will create or overwrite files in local directories, which is especially sensitive given the skill has write and exec capabilities.

Missing User Warnings

Medium
Confidence
95% confidence
Finding
Documenting a callback_url parameter without an explicit warning means users may not realize collected results can be transmitted over the network to an external endpoint. In a skill that aggregates browsing-derived content and execution logs, silent network egress increases the risk of unintended data disclosure or SSRF-style misuse if arbitrary callback URLs are accepted.

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.