ClawHub
Back to skill

Security audit

Mibatt Dietu Cli Agent

Security checks across malware telemetry and agentic risk

Overview

This appears to be a purpose-aligned CLI/auth documentation skill, with a credential-handling documentation weakness but no evidence of hidden or malicious behavior.

Install only if you are comfortable using this skill for authenticated CLI workflows. Prefer short-lived, least-privilege tokens stored in protected environment variables or a secret manager, avoid pasting real tokens directly into commands, and rotate or revoke tokens after automation use.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
Findings (1)

Missing User Warnings

Medium
Confidence
91% confidence
Finding
The documentation explicitly recommends long-lived PATs for automation and shows passing tokens via an inline environment assignment and a `--token` CLI flag without warning about secret exposure. In agent, CI, and multi-user shell contexts, command-line arguments and shell history/process inspection can leak credentials, and long-lived tokens increase the blast radius if exposed.

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.