ClawHub
Back to skill

Security audit

竖版视频生成免费版

Security checks for vulnerabilities and agentic risk

Overview

This video-generation skill is not clearly malicious, but it asks for broad command execution and exposes an under-scoped custom TTS command template that users should review carefully.

Install only if you are comfortable with a skill that can guide the agent to run local commands for media generation. Avoid using arbitrary --tts-command templates with untrusted script text, review any command before execution, and install FFmpeg or browser dependencies only through package sources you trust.

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
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • 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
Findings (5)

Intent-Code Divergence

High
Category
Not specified by scanner
Confidence
97% confidence
Finding

The skill explicitly exposes a --tts-command template that interpolates attacker-controlled fields such as {text}, {output}, {voice}, and {rate} into an executable command string. In a skill with exec access, this creates a clear command-injection path if any of those values contain shell metacharacters or if the template is passed through a shell, enabling arbitrary command execution on the host.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The description says to use the skill whenever there is a need for '视频处理、音频编辑、媒体转换、配音生成', which are very broad, everyday task categories rather than narrow trigger phrases or constrained activation conditions. This creates a risk of unintended invocation because the scope is not clearly bounded and no exclusion examples are provided beyond copyrighted media.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
97% confidence
Finding

The description explicitly states '支持中文交互' and the document repeatedly frames usage in Chinese without indicating that the user may choose another language. This is a natural-language locale constraint that appears to force a specific language without opt-in or documented justification.

Content

No source excerpt is available for this finding.

Sudo/Root Execution

Medium
Category
Privilege Escalation
Confidence
70% confidence
Finding

Commands invoke sudo or root privileges. Verify this elevated access is necessary and justified.

Content

Scanner excerpt · SKILL.md (reported line 121)May include surrounding context.

md
# FFmpeg:视频合成
brew install ffmpeg      # macOS
# 或
sudo apt install ffmpeg  # Linux

# Chrome:HTML截图(使用预制图片时可跳过)
# 自动检测系统Chrome路径,或设置环境变量:

Description-Behavior Mismatch

Medium
Category
Not specified by scanner
Confidence
89% confidence
Finding

The manifest describes a narrow Markdown-to-video skill, but the documentation expands its behavior to generic file handling, API access, browser use, and arbitrary command execution. This capability sprawl is dangerous because it normalizes broader privileged actions than users would reasonably expect, increasing the chance of misuse, over-permissioning, and abuse through prompt-driven task expansion.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.