ClawHub
Back to skill

Security audit

Story to Prompts

Security checks for vulnerabilities and agentic risk

Overview

This is a low-risk creative-writing skill that turns stories or scenes into bilingual text-to-image prompts without requesting tools, credentials, network access, persistence, or local data access.

Installers should expect this skill to automatically produce polished bilingual image prompts without a confirmation step. Review generated prompts before using them with an image model, especially for style, language preference, and negative-prompt suitability.

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
Confidence
85% confidence
Finding

Skill contains instructions that could directly expose system prompts, internal rules, or hidden instructions to users or external parties.

Content

Scanner excerpt · SKILL.md (reported line 130)May include surrounding context.

[Style] + [Shot type + Composition + Camera angle] + [Subject + fixed features] + [Action/Expression] + [Environment/Background] + [Lighting/Atmosphere] + [Material/Texture] + [Quality tags] + [Negative prompt]

text

**Bilingual output rules:**
- Primary language prompt: complete and detailed, ready to copy-paste
- Secondary language prompt: equally complete, adapted to target language prompt conventions (not a literal translation)

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The skill advertises very broad trigger phrases such as 'text-to-image prompt', 'generate prompts for this scene', and generic bilingual variants, which can cause the agent to invoke this skill for a wide range of ordinary creative requests. Over-broad activation increases the chance of prompt hijacking, unintentional routing, or bypass of more appropriate, narrower skills because this skill is designed to directly emit polished copy-paste prompts without confirmation.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
96% confidence
Finding

This markdown file uses Chinese throughout, including the title and all table headings/content, with no indication that the user can choose another language or that the skill is intentionally limited to a Chinese-speaking context. Under the policy, forcing a specific language without user opt-in is a natural-language policy violation.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The file is entirely written in Chinese and presents the guidance as the default reference without any indication that language selection is optional. Under the policy, forcing a specific language or locale without user opt-in is a natural-language policy violation unless the locale constraint is explicitly justified.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
79% confidence
Finding

This markdown file is written entirely in Chinese and includes an instruction directing behavior: '用户未指定风格时，根据故事内容自动选择最合适的风格。' There is no indication that users may choose another language or locale, which can conflict with policies against forcing a specific language without opt-in.

Content

No source excerpt is available for this finding.