ClawHub
Back to skill

Security audit

kimi-cli-doc-helper

Security checks across malware telemetry and agentic risk

Overview

This is a documentation-helper skill for Kimi CLI with no executable payload, persistence, credential access, or hidden privileged behavior.

Safe to install as a Kimi CLI documentation helper. Expect it to fetch public Kimi CLI docs when relevant, and review any remote installation command manually before running it.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • 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
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (2)

Vague Triggers

Medium
Confidence
95% confidence
Finding
The trigger condition is overly broad because 'terminal AI assistants for coding' is not limited to Kimi CLI-specific requests. This can cause the skill to activate for unrelated tools and unnecessarily force external documentation fetching, increasing prompt-scope bleed and the chance of irrelevant or biased guidance.

Vague Triggers

Medium
Confidence
92% confidence
Finding
The condition 'Answering questions where Kimi CLI is part of the solution' is ambiguous and lacks boundaries for when the skill should engage. In practice, this can over-trigger the skill whenever Kimi CLI is merely mentioned as one option, steering the agent into mandatory web retrieval and tool-specific framing without clear user intent.

VirusTotal

65/65 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.