ClawHub
Back to skill

Security audit

open-huggingface

Security checks for vulnerabilities and agentic risk

Overview

This skill is a narrow browser helper that opens Hugging Face in Brave and does not request credentials or modify content.

Before installing, understand that the skill may reuse your existing authenticated Brave session to open Hugging Face, but it says not to enter credentials or change account/content settings. Install only if you want that browser automation behavior.

A.I.G

Vulnerability Patterns
  • Skill Instruction HijackingAlters the agent's session goals or safety constraints when the skill loads
  • Agent Memory PoisoningWrites attacker-controlled rules into memory that affect later sessions
  • Remote Payload Retrieval and ExecutionFetches external code whose behavior can change after review
  • Embedded Malicious CodeShips malicious scripts inside the skill and executes them locally
  • Unauthorized Access and Privilege EscalationObtains permissions beyond the task's legitimate needs

SkillSpector

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
92% confidence
Finding
The description says to use the skill when the user asks to "open, visit, or go to Open Hugging Face," but the trigger phrase itself is inconsistent and awkwardly phrased, and it does not clearly enumerate precise invocation examples or exclusions. This creates ambiguity about what exact user utterances should activate the skill versus ordinary browsing requests.

Static analysis

No suspicious patterns detected.