ClawHub
Back to skill

Security audit

NEXUS Error Explain

Security checks across malware telemetry and agentic risk

Overview

This is a transparent paid error-explainer skill, but it can automatically send error text to an external AI service and use payment credentials without clear per-use approval.

Install only if you trust NEXUS with the error text you send and are comfortable with paid requests. Prefer sandbox or tightly scoped payment credentials, require explicit approval before each paid external call, and redact secrets, customer data, tokens, internal hostnames, and production diagnostics before use.

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 (1)

Vague Triggers

Medium
Confidence
79% confidence
Finding
The README states that the skill is 'automatically invoked' when a matching task is detected, but it does not define concrete trigger boundaries, confirmation requirements, or what data may be sent off-platform. In an agent setting, ambiguous auto-invocation can cause unreviewed external calls and unintended transmission of user-provided error content to a paid remote service.

VirusTotal

VirusTotal findings are pending for this skill version.

View on VirusTotal

Static analysis

No suspicious patterns detected.