ClawHub
Back to skill

Security audit

Ephemeral Engineering

Security checks across malware telemetry and agentic risk

Overview

This skill is a disclosed engineering-tool authoring workflow with strong verification warnings and no executable install or hidden behavior.

Install only if you want Codex to help create engineering calculation/report HTML tools. Treat generated tools as drafts: the skill itself requires engineer verification, a digit-for-digit hand calculation check, and keeping the draft watermark until verification is complete.

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
89% confidence
Finding
The invocation text is intentionally very broad, directing use for many loosely related requests and even when the user does not explicitly name the skill. This can cause the agent to route ambiguous prompts into a powerful code-generating engineering workflow, increasing the chance of inappropriate activation, mistaken scope selection, or unsafe deliverable generation without sufficient user confirmation.

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.