ClawHub
Back to skill

Security audit

知犀思维导图

Security checks across malware telemetry and agentic risk

Overview

This skill does what it advertises for Zhixi mind-map cloud files, but users should treat its API token and import feature carefully.

Install only if you want an agent to access your Zhixi cloud files. Prefer the environment variable used by the script, ZHIXI_API_KEY, or a secure secret store instead of a plaintext token file, and only run the import command for Markdown files you intend to upload to Zhixi.

SkillSpector

By NVIDIA
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 (2)

Vague Triggers

Medium
Confidence
82% confidence
Finding
The activation phrases are broad enough to match common conversation terms like 'mind map' or related file-operation requests, increasing the chance of unintended invocation. In a skill that can access cloud files and tokens, accidental triggering can expose metadata, initiate searches, or cause the system to handle sensitive data when the user did not intend to use this integration.

Missing User Warnings

Medium
Confidence
94% confidence
Finding
The skill recommends storing an API token in a local file in the skill directory without warning about credential sensitivity or file-permission controls. Local plaintext secrets are easily exposed through repository inclusion, backup leakage, directory listing, or accidental read by other tools, which could grant unauthorized access to a user's Zhixi cloud files.

VirusTotal

52/52 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

Detected: suspicious.env_credential_access, suspicious.potential_exfiltration

Environment variable access combined with network send.

Critical
Code
suspicious.env_credential_access
Location
scripts/zhixi-files.js:11

Sensitive-looking file read is paired with a network send.

Warn
Code
suspicious.potential_exfiltration
Location
scripts/zhixi-files.js:16