ClawHub
Back to skill

Security audit

高品质短视频制作 · 声画同步工业级流水线

Security checks for vulnerabilities and agentic risk

Overview

This is a disclosed video-production workflow skill with no packaged executable code or hidden persistence; the main issues are broad triggers and Chinese-only guidance that may affect routing or usability.

Install only if you want a Chinese-language, narration-driven video production workflow. Expect to review or narrow triggers in multi-skill setups, verify that the referenced scripts/templates actually exist in your environment, and use only trusted TTS commands or dependencies when providing API keys through environment variables.

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 (2)

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
83% confidence
Finding

The skill is written entirely in Chinese and describes usage and outputs without offering a language-selection mechanism, which can force Chinese-language behavior on users whose requests are in another language. In a multi-skill environment, this can degrade reliability and cause unintended responses, especially when the broad trigger set also matches English requests like 'product video' and 'promotional video'.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The trigger phrases are very broad and include generic requests like '教程视频', '短视频制作', 'product video', and 'promotional video', which are likely to match many ordinary video-related queries beyond this skill’s narrow workflow. This can cause the agent to invoke the skill in unintended contexts, leading to inappropriate routing, user confusion, and suppression of better-matched skills or general assistance.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.