ClawHub
Back to skill

Security audit

Kimi Quota

Security checks across malware telemetry and agentic risk

Overview

This skill appears to be a straightforward Kimi quota checker, but it requires and can save a Kimi login cookie, so users should treat it like account access.

Install only on a trusted machine. Use only the Kimi cookie requested, install cryptography before using --save, and run the documented --clear command when you no longer want the saved login state. Avoid saving the cookie on shared or managed systems.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (1)

Lp3

Medium
Category
MCP Least Privilege
Confidence
91% confidence
Finding
The skill performs sensitive actions including reading environment variables, storing authentication cookies on disk, invoking shell commands, and making network requests, yet the manifest shown in SKILL.md declares no explicit permissions or trust boundaries. This is dangerous because users and the hosting platform cannot accurately assess or constrain the skill's access, and the skill handles a high-value credential (`kimi-auth`) that could expose account data if misused or improperly stored.

VirusTotal

60/60 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.