ClawHub
Back to skill

Security audit

Super Ai Dev Runtime

Security checks across malware telemetry and agentic risk

Overview

This is a disclosed development automation skill that can edit code and run terminal/test commands, so it is powerful but coherent with its stated purpose.

Install only if you intend to delegate coding tasks to a trusted local AiDevRuntime server. Review requested tasks and resulting edits before relying on them, avoid pointing it at sensitive repositories unless you trust its memory behavior, and treat any configured API key as a credential for that external runtime.

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 (2)

Vague Triggers

Medium
Confidence
93% confidence
Finding
The invocation pattern `/ai-dev-runtime <task>` is overly broad and can encourage handing arbitrary high-level instructions to a skill that has file editing, terminal execution, and test-running capabilities. In this context, the broad trigger increases the chance of unsafe or unintended operations because users are not constrained or warned about the scope of actions the runtime may perform.

Missing User Warnings

Medium
Confidence
97% confidence
Finding
The skill advertises productivity benefits but does not prominently warn that it can execute terminal commands and modify code/files. Because this skill exposes powerful capabilities such as `run_terminal`, `edit`, `apply_patch`, and `run_tests`, the missing warning materially increases the risk of users invoking it without understanding that it may run commands or alter the workspace.

VirusTotal

63/63 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.