ClawHub
Back to skill

Security audit

Lizhi

Security checks for vulnerabilities and agentic risk

Overview

This is a narrow Markdown-only skill for summarizing public Lizhi FM pages, with no code, persistence, credential use, or destructive behavior found.

Before installing, treat this as a public web summarization helper only. Use it for visible Lizhi FM pages, keep requests low volume, and do not use it for downloads, logged-in pages, API scraping, reverse engineering, or bypassing human verification.

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
Category
Not specified by scanner
Confidence
94% confidence
Finding

The description says the skill should be invoked whenever a user needs to 'access or automate Lizhi-related content,' which is overly broad and not tightly scoped to the limited, public-page summarization use cases described later in the file. This can cause the agent to trigger the skill in inappropriate contexts, potentially expanding automation against a third-party site beyond intended boundaries and increasing the chance of policy, compliance, or misuse issues.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.