ClawHub
Back to skill

Security audit

NEXUS Code Explain

Security checks across malware telemetry and agentic risk

Overview

This is a disclosed paid remote code-explanation skill, but it needs review because it can send code and payment authorization to a third-party service without clear per-request control.

Install only if you trust NEXUS with the code or text you submit and with the payment proof used for requests. Use sandbox_test or a tightly scoped payment proof where possible, avoid sending secrets or proprietary code, and configure your agent to ask before remote paid calls if supported.

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 README states the skill is 'automatically invoked' when a matching task is detected, but gives no concrete trigger boundaries, consent model, or safeguards. In an agent ecosystem, ambiguous auto-invocation can cause unintended routing of user prompts or code to this remote skill, increasing the chance of silent data disclosure or unexpected paid requests.

Missing User Warnings

Medium
Confidence
96% confidence
Finding
The README describes sending an 'input' payload to an external hosted endpoint but does not clearly warn users that their code/query contents are transmitted to a third-party service. For a code-explainer skill, inputs may contain proprietary source, secrets, or sensitive business logic, so omission of this warning materially increases privacy and confidentiality risk.

VirusTotal

VirusTotal findings are pending for this skill version.

View on VirusTotal

Static analysis

No suspicious patterns detected.