ClawHub
Back to skill

Security audit

omadeus

Security checks across malware telemetry and agentic risk

Overview

This skill is a straightforward Maestro API connector, with expected credential use and external requests for creating tasks, listing tasks, and sending room messages.

Install this only if you want your agent to use your configured Maestro account. Content used to create tasks or send room messages will be sent to the configured Maestro API, so avoid including secrets or sensitive data unless that is intended and authorized.

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 says to use itself whenever a user wants to interact with Maestro, but it does not define meaningful constraints or confirmation boundaries for when external actions should occur. In an agent environment, this broad activation can cause the skill to engage on loosely related requests and send user-derived content to the external Maestro API without sufficiently explicit scoping, increasing the chance of unintended task creation or message sending.

Missing User Warnings

Medium
Confidence
92% confidence
Finding
The skill description and guidance do not warn that task descriptions and room messages will be transmitted to a third-party Maestro service. Without that disclosure, users may provide sensitive or regulated information under the assumption it remains local, leading to unintended data exposure to an external system.

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:36