ClawHub
Back to skill

Security audit

Giggle Generation Scripts

Security checks for vulnerabilities and agentic risk

Overview

This is a markdown-only creative writing skill for Chinese screenplay drafting, with no executable code, persistence, credential access, or hidden data flows.

Install this if you want a specialized Chinese screenplay-writing assistant with a strong Jiang Wen-inspired dialogue framework. Be aware it may steer broad scriptwriting prompts into that specific style unless you explicitly ask for a different language or tone.

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
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • System Prompt LeakageDirect Leakage, Indirect Extraction, Tool-Based Exfiltration
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Findings (5)

Direct Prompt Extraction

High
Category
System Prompt Leakage
Content
- Absurdity comes from logically consistent nonsense—each line alone sounds "reasonable", together it's absurd
- Forbidden: internet memes, puns, slapstick (not Stephen Chow; Jiang Wen style)

### Language Fingerprint Rule

- Each character's speech pattern must be recognizable in every line
- Cover character names; the lines alone should identify who speaks
Confidence
85% confidence
Finding
Skill contains instructions that could directly expose system prompts, internal rules, or hidden instructions to users or external parties.

Vague Triggers

Medium
Confidence
94% confidence
Finding
The skill description uses broad trigger phrases like 'generate script', 'write script', and 'revise script or similar', which can cause the agent to activate in contexts far beyond the narrowly intended use case. Over-broad activation increases the chance this skill will intercept unrelated creative-writing requests and impose its own rigid behavior, creating prompt-routing and policy-bypass risks at the orchestration layer.

Natural-Language Policy Violations

Medium
Confidence
91% confidence
Finding
The skill metadata hard-codes Chinese script generation and a specific Jiang Wen–style dialogue framework without requiring user opt-in. This can override user preferences on language, locale, and stylistic constraints, causing inappropriate or misleading outputs when invoked for general script help.

Vague Triggers

Medium
Confidence
95% confidence
Finding
The skill description is broadly scoped to common requests like generating scripts, scenes, dialogue drafts, or revisions, which can overlap with many benign creative-writing prompts. Overly broad trigger criteria increase the chance of unintended activation, causing the wrong skill to take over user intent and potentially override safer or more appropriate handling paths.

Natural-Language Policy Violations

Medium
Confidence
83% confidence
Finding
文件顶部以“简体中文 | English”呈现，并整体以中文规定输出行为，但文内未说明这是用户可选语言还是仅文档翻译版本，也未写明需经用户选择后才固定语言。按规则，未经用户 opt-in 而强制特定语言/locale 可能构成自然语言政策问题。

Static analysis

No suspicious patterns detected.