ClawHub
Back to skill

Security audit

物理动画制作工作流

Security checks for vulnerabilities and agentic risk

Overview

This skill is a straightforward workflow for making physics HTML Canvas animations and does not request unusual permissions or hidden actions.

Installers should expect a mostly Chinese workflow for creating physics animation files. Review generated HTML before sharing or running it in sensitive contexts, as with any user-created code, but this skill itself does not show hidden or overbroad 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)

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
93% confidence
Finding

The manifest description at L004 is entirely in Chinese and instructs when the skill should be used, which can impose a language expectation on users without explicit opt-in. Although an English section appears later, the activation-facing metadata is still Chinese-first and does not state that users may choose their preferred language.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.