ClawHub
Back to skill

Security audit

Liblib Ai Gen

Security checks for vulnerabilities and agentic risk

Overview

This skill is a straightforward LiblibAI image and video generation client, with expected API-key and network use disclosed in the artifacts.

Install only if you intend to use LiblibAI and are comfortable providing LiblibAI API credentials. Do not include sensitive prompts, private image URLs, regulated data, or internal assets unless you intend to send them to LiblibAI for processing.

SkillSpector

Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Findings (3)

Lp3

Medium
Category
MCP Least Privilege
Confidence
95% confidence
Finding
The skill requires environment secrets and makes outbound network requests, but it declares no permissions. This creates a transparency and control gap: reviewers and runtime policy systems cannot accurately assess that the skill can access API keys and transmit user data to an external service.

Vague Triggers

Medium
Confidence
74% confidence
Finding
The trigger description is broad enough to match many ordinary image or video creation requests, which can cause the skill to activate in more situations than users expect. Because the skill sends prompts and possibly image URLs to an external API, over-broad invocation increases the chance of unintended third-party data disclosure.

Missing User Warnings

Medium
Confidence
96% confidence
Finding
The documentation explains how to submit prompts and image URLs to LiblibAI but does not clearly warn that this content is transmitted to a third-party service. Users may unknowingly send sensitive prompts, internal image URLs, or private assets off-platform, creating privacy and data-governance risk.

Static analysis

No suspicious patterns detected.