ClawHub
Back to skill

Security audit

KiloCode

Security checks across malware telemetry and agentic risk

Overview

This is an instruction-only skill for using the Kilo coding CLI, and its powerful coding-agent abilities are disclosed and aligned with that purpose.

Before installing, confirm that the `kilo` CLI comes from a trusted source, run it only in projects where code edits and commands are acceptable, review which provider auth profile may receive prompts or code context, and reserve `--auto` for trusted CI/CD or disposable environments.

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
84% confidence
Finding
The skill description is broad enough to match a wide range of generic coding requests, which can cause the agent to invoke a powerful code-execution tool in situations where a narrower or safer capability would be more appropriate. Because this skill can run commands and modify files, over-triggering increases the chance of unintended system changes or unsafe autonomous actions from ambiguous user prompts.

Missing User Warnings

Medium
Confidence
93% confidence
Finding
The skill explicitly advertises autonomous execution, file writes, terminal command execution, and browser interaction, but does not prominently warn that these actions can alter code, affect local state, access external resources, or cause destructive side effects. In the context of an agent skill, this is dangerous because users or orchestration logic may invoke it without understanding that it has high-impact capabilities, especially when `--auto` suppresses permission prompts.

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.