ClawHub
Back to skill

Security audit

Huggingface

Security checks across malware telemetry and agentic risk

Overview

This is a straightforward Hugging Face CLI reference skill, with real account-changing commands that users should run carefully.

Install only if you want the agent to use your local Hugging Face CLI. Use a least-privilege token, keep it out of logs and source control, confirm exact repository names before delete or move commands, and review files and repository visibility before running uploads.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • 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
Findings (3)

Missing User Warnings

Medium
Confidence
88% confidence
Finding
The skill documents a destructive `hf repos delete` operation without any surrounding warning about permanence, scope validation, or confirmation safeguards. In an agent context, terse examples can be copied or invoked automatically, increasing the risk of accidental deletion of the wrong Hugging Face repository or namespace.

Missing User Warnings

Medium
Confidence
91% confidence
Finding
The upload examples encourage sending local files and directories to remote Hugging Face repositories but do not warn about accidental disclosure of proprietary code, private datasets, secrets, or personal data. Because this skill is specifically about publishing artifacts to an external service, omission of privacy and content-review guidance materially increases the chance of unintended data exfiltration.

Missing User Warnings

Low
Confidence
80% confidence
Finding
The skill requires `HF_TOKEN` for authentication but provides no guidance on secure credential handling, such as avoiding hardcoding, shell history leakage, logs, or over-scoped tokens. In agent and CLI workflows, missing credential-safety guidance can lead to token exposure and unauthorized access to Hugging Face resources.

VirusTotal

66/66 vendors flagged this skill as clean.

View on VirusTotal