ClawHub
Back to skill

Security audit

Tianshu Short Script

Security checks for vulnerabilities and agentic risk

Overview

This skill is a local Chinese short-video storyboard helper with no evidence of hidden data access, network activity, persistence, or destructive behavior.

Install this if you want a local helper for Chinese short-video talking-head storyboard tables. Be aware that its prompts and generated template text are Chinese-focused and platform-specific; users needing other languages may need manual adaptation.

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 (4)

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
88% confidence
Finding

The "When to Run" section lists triggers like "分镜怎么拆" and "抖音口播大纲", which are fairly broad user utterances and could overlap with general content-planning requests rather than this specific storyboard-table skill. While the file includes a NOT for section, it does not provide tighter activation constraints or negative examples for nearby cases such as general scriptwriting versus shot-by-shot storyboard generation.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
97% confidence
Finding

This code file contains natural-language strings exclusively in Chinese in the header comment, usage message, platform hints, and generated output. Under the policy, forcing a specific language without user opt-in is a natural-language policy violation unless the locale restriction is clearly documented and justified, which is not present here.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
77% confidence
Finding

The natural-language description and invocation examples are written entirely in Chinese and imply the skill is intended to operate in that language, but the file does not explicitly state that this is a Chinese-only or region-specific skill nor offer a language opt-in. Under the language policy criteria, forcing a specific language without user choice can be a policy concern unless it is clearly documented and justified.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
80% confidence
Finding

The manifest includes prominent Chinese-language user-facing text in the tagline and tags while the description is in English, but it does not state whether output language is fixed, user-selectable, or region-specific. This can create a locale-policy issue if the skill implicitly assumes Chinese-language interaction without offering user choice or documenting the constraint.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.