ClawHub
Back to skill

Security audit

NEXUS Orchestrator

Security checks across malware telemetry and agentic risk

Overview

This skill does what it says, but it can route broad tasks to a paid third-party AI service with unclear automatic trigger and spending controls.

Review before installing. Use it only if you trust NEXUS, are comfortable sending task prompts to ai-service-hub-15.emergent.host, and have clear controls for payment proofs or wallet flows. Avoid submitting secrets, private code, regulated data, or sensitive business content unless that sharing is approved.

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 (3)

Vague Triggers

Medium
Confidence
89% confidence
Finding
The README states the skill is 'automatically invoked' when a matching task is detected, but it does not define what constitutes a match or what safeguards gate execution. In a skill that brokers remote orchestration, ambiguous trigger boundaries can cause unintended activation and transmission of user requests to an external service without informed user intent.

Missing User Warnings

Medium
Confidence
96% confidence
Finding
The documentation promotes automatic orchestration and remote API calls but does not warn that user task content will be sent to a third-party service endpoint. Because the skill's core function is to relay user goals to an external orchestrator, lack of disclosure materially increases the risk of privacy leakage, unauthorized data sharing, and compliance violations when sensitive prompts are processed.

Vague Triggers

Medium
Confidence
90% confidence
Finding
The skill is described so broadly ('chain multiple AI services into automated workflows') that it can match many generic user intents and be invoked in situations where users may not realize their data will be sent to a third-party orchestrator. In a high-autonomy agent ecosystem, overbroad routing increases the chance of unintended delegation of sensitive prompts or tasks to an external paid service.

VirusTotal

VirusTotal findings are pending for this skill version.

View on VirusTotal

Static analysis

No suspicious patterns detected.