ClawHub
Back to skill

Security audit

Hugging Face Memory Estimator

Security checks for vulnerabilities and agentic risk

Overview

This skill is a narrow Hugging Face memory-estimation helper with disclosed command use and no detected suspicious behavior.

Install this if you want Codex to estimate Hugging Face model memory needs. Be aware that using it runs an external CLI through `uvx`, contacts Hugging Face, and may use `HF_TOKEN` only when accessing gated or private models.

SkillSpector

Vulnerability Patterns
  • 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
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep

Static analysis

No suspicious patterns detected.