ClawHub

Cis Openeuler Audit

Security checks across malware telemetry and agentic risk

Overview

This is a legitimate OpenEuler CIS audit skill, but its generated baselines can contain sensitive local security configuration and should be protected.

Install and run this only on OpenEuler systems you are authorized to audit. Treat generated baseline and report directories as sensitive because they may include sudo policy, user/account details, SSH and firewall configuration, audit rules, and limited shadow-derived indicators; store them with restrictive permissions and avoid sharing them broadly.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
  • 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
Findings (3)

Context-Inappropriate Capability

Medium
Confidence
94% confidence
Finding
The script writes highly sensitive local security data into baseline files, including partial password-hash material from /etc/shadow, UID 0 accounts, sudo policy, and user/account details. Even though this appears intended for compliance auditing rather than abuse, creating a plaintext snapshot of these secrets and authorization settings materially increases exposure if the output directory is readable by other users, archived insecurely, or exfiltrated.

Vague Triggers

Medium
Confidence
78% confidence
Finding
The trigger phrases are broad and can invoke the skill for generic requests like checking a machine's security baseline, without constraining target scope, authorization, or environment. In this skill, unintended invocation is more dangerous because the documented workflow includes running a sudo-backed baseline collection script on a target host, which could prompt privileged operations on the wrong system.

Missing User Warnings

Medium
Confidence
91% confidence
Finding
The script is designed to collect broad security configuration and account metadata, but its usage/comments do not warn operators that the generated baseline may contain sensitive system and authorization information. This raises the risk of accidental disclosure because users may treat the output as a routine report and share or store it without appropriate protections.

VirusTotal

66/66 vendors flagged this skill as clean.

View on VirusTotal