ClawHub
Back to skill

Security audit

treg

Security checks across malware telemetry and agentic risk

Overview

The skill has a coherent tool-catalog purpose, but it asks for broad command authority, unverified installation, and secret/account handling that users should review carefully.

Install only if you are comfortable giving treg broad access to broker API calls, store or inject credentials, and modify connected tools/accounts. Review the install script before running it, avoid blanket CLI approval for sensitive operations, confirm prices before paid calls, and use narrowly selected directories when uploading secrets or skills.

SkillSpector

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 skill description is extremely broad and encourages using this plugin first for almost any external-data, scraping, SEO, social, enrichment, ads, or connected-account task. That increases the chance an agent will invoke it in situations where narrower, safer, or more transparent tools would be more appropriate, especially because the skill also supports acting on connected accounts and spending team balance.

Missing User Warnings

High
Confidence
98% confidence
Finding
The skill directly instructs users to execute a remote install script via `curl ... | sh`, which is a classic supply-chain and arbitrary code execution risk. Because the command streams code from the network straight into a shell with no integrity verification, version pinning, signature check, or review step, compromise of the host, CDN, or script would lead to immediate code execution on the user's machine.

Missing User Warnings

High
Confidence
96% confidence
Finding
The skill promotes bulk upload that scans local `.env` files and skill directories, which can easily capture unrelated secrets or sensitive files and transmit them to the service. In a tool explicitly designed to ingest credentials and secrets, encouraging broad directory scanning without strong scoping, preview, or warnings materially increases the risk of accidental secret exfiltration.

VirusTotal

VirusTotal findings are pending for this skill version.

View on VirusTotal

Static analysis

No suspicious patterns detected.