ClawHub
Back to skill

Security audit

Github Dev Standard Free

Security checks across malware telemetry and agentic risk

Overview

This is a development-process checklist skill with command examples, and I found no hidden code, persistence, or deceptive behavior.

Install only if you want an agent to apply a structured development workflow and run normal local development checks. Review commands before execution, especially any GitHub, git, test, or publish-related step, and do not treat the generic CRUD wording as permission for unrelated actions.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
  • 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)

Description-Behavior Mismatch

Medium
Confidence
90% confidence
Finding
The skill is presented as a project-development standards checklist, but the body expands its scope into generic operational behaviors such as create/query/modify/delete and export/save/convert. This broadening creates capability confusion and can cause an agent to treat a passive guidance document as authorization to perform real state-changing actions, increasing the chance of unintended file, config, or workflow modifications.

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.