ClawHub
Back to skill

Security audit

ht-skills

Security checks across malware telemetry and agentic risk

Overview

This skill is a disclosed API client for managing a user's 灏天文库 collections, documents, images, and promotion requests, with cautions around token handling and write actions.

Install only if you trust the publisher and are comfortable giving the skill a 灏天文库 API token. Review write operations before approving them, especially collection renames, document updates or moves, image uploads, and garden-to-featured promotion requests because those affect your account content.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
  • 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
Findings (2)

Tp4

High
Category
MCP Tool Poisoning
Confidence
87% confidence
Finding
The declared description omits materially sensitive capabilities: updating collection metadata and, more importantly, submitting promotion requests that can permanently change how a collection is managed. This mismatch can mislead users or higher-level policy layers into authorizing a skill they believe only manages documents/images, increasing the risk of unintended state-changing operations.

Unpinned Dependencies

Low
Category
Supply Chain
Content
requests>=2.28.0
Confidence
93% confidence
Finding
The dependency is specified as `requests>=2.28.0`, which is unpinned and allows installation of different versions across environments and over time. This weakens build reproducibility and can unintentionally admit vulnerable or breaking releases, especially in a skill that performs network operations and uploads/retrievals against external services.

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.