ClawHub
Back to skill

Security audit

Remotion 逐词高亮字幕

Security checks for vulnerabilities and agentic risk

Overview

This is a disclosed local subtitle-generation skill for Chinese-oriented video workflows, with no evidence of hidden persistence, exfiltration, or destructive behavior.

Before installing, be aware that this skill is optimized for Chinese-language subtitle generation and local media rendering. Use it only on video files and output folders you choose, and change the Whisper language option when processing non-Chinese videos.

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
  • MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
  • 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 (4)

Undeclared Tool Scope

Medium
Category
MCP Least Privilege
Confidence
89% confidence
Finding

The skill clearly instructs the agent to read local media files, create project files, write transcripts/captions, and render output videos, but it does not declare an explicit tool scope such as permissions or allowed-tools. That mismatch weakens least-privilege enforcement and can let an agent with broader ambient filesystem access perform more file operations than users or platform policy expect.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The markdown explicitly sets transcription to 'Chinese by default' with --language zh, which imposes a language/locale choice on users. The file does not state that this default is optional or that the user can choose another language, so it conflicts with the language-choice policy.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
94% confidence
Finding

The display name, description, and default prompt are all written in Chinese, which indicates the skill is designed to operate in a specific language. There is no visible opt-in, alternative language option, or justification that this skill is intentionally restricted to a Chinese-speaking context.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
82% confidence
Finding

The README states the skill is designed for Chinese creator workflows, which signals a language/locale preference. While this may be intentional, the description does not explicitly frame it as an opt-in choice or a strictly region-specific tool, so it can be read as a default language constraint.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.