ClawHub
Back to skill

Security audit

Makaron

Security checks across malware telemetry and agentic risk

Overview

The skill appears to be a Makaron media workflow helper whose remote upload and persistent project behavior fits its purpose, but users should understand that media may be sent to and stored by Makaron.

Install only if you are comfortable with prompts and media being processed by Makaron and potentially kept in a persistent project. For confidential, private, or regulated media, ask the agent to confirm before upload and review Makaron's retention and deletion options.

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
90% confidence
Finding
The trigger description is very broad, covering nearly any creative media task, which can cause the skill to activate in contexts where the user did not explicitly consent to using Makaron. Because this skill uploads inputs to a third-party remote service and works with persistent projects, over-invocation increases the chance of unnecessary data exposure and unintended external processing.

Missing User Warnings

Medium
Confidence
97% confidence
Finding
The skill repeatedly instructs the agent to upload images, videos, audio, and project context to Makaron, and explicitly notes that outputs are saved to a persistent project, but it does not present a clear upfront warning about remote transmission and retention. In an agent setting, this can lead to confidential or personal media being sent to a third-party service without informed user consent.

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

Detected: suspicious.exposed_secret_literal

File appears to expose a hardcoded API secret or token.

Critical
Code
suspicious.exposed_secret_literal
Location
SKILL.md:42