ClawHub
Back to skill

Security audit

WJS Translating Subtitles

Security checks for vulnerabilities and agentic risk

Overview

This skill is a focused subtitle translation helper with no evidence of hidden access, persistence, or unsafe behavior.

Safe to install for subtitle translation workflows. Before running the Python helper directly, confirm your project intentionally provides the referenced integration/translate_srt.py implementation, and specify Traditional Chinese if that is the desired Chinese script.

SkillSpector

Vulnerability Patterns
  • 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
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
Findings (1)

Natural-Language Policy Violations

Medium
Confidence
88% confidence
Finding
The instructions explicitly require 'Simplified characters only' for Chinese output unless the user asks otherwise. This imposes a specific language/script locale by default rather than offering a Chinese locale choice, which can conflict with language/locale policy expectations when users request 'Chinese' generically.

Static analysis

No suspicious patterns detected.