ClawHub
Back to skill

Security audit

IP 形象资产Ip Character Image System

Security checks for vulnerabilities and agentic risk

Overview

This skill is a coherent prompt-writing workflow for IP character image assets and does not include code execution, credential use, persistence, or hidden data handling.

Install only if you want a Chinese-forward workflow for character/IP image prompt production. Be mindful that user-uploaded reference images may be used as visual inputs to whatever image-generation tool you choose, but the skill itself does not add hidden execution or data access.

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
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • System Prompt LeakageDirect Leakage, Indirect Extraction, Tool-Based Exfiltration
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (6)

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 224)May include surrounding context.

md
- Preserve side-view depth and limb placement when creating pose sheets or toy renders.
- Preserve back-view details for packaging turns, figure renders, and specification sheets.
- Use image-reference wording such as "based on the provided three-view reference image" and "preserve the exact character structure from the reference".
- Output prompts that expect the submitted image to be attached as the visual reference in the image-generation tool.
- If a model supports image strength/reference strength, recommend medium-high reference strength for identity assets and medium reference strength for scenes/merchandise.

## Default Style Presets

Credential Access

High
Category
Privilege Escalation
Confidence
70% confidence
Finding

Code accesses credential files (SSH keys, AWS credentials, etc.). This could indicate credential theft attempts.

Content

Scanner excerpt · references/prompt-blueprints.md (reported line 230)May include surrounding context.

Purpose: test whether the IP works across products.

text
[Character identity module], [Visual feature module], mascot merchandise presentation style, merchandise mockup display, includes sticker sheet, acrylic keychain, postcard, tote bag, mug or phone case as appropriate, consistent character artwork across all items, mixed materials matching each product, clean studio tabletop lighting, clean studio tabletop background, cohesive palette, commercial product presentation, [Consistency module], no unreadable text, no watermark, do not redesign the character.

12. Social Media Key Visual/Poster

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
97% confidence
Finding

The skill description is written entirely in Chinese and does not indicate that other languages are supported or that the user may choose their preferred language. Under the stated policy, forcing a specific language without user opt-in is a natural-language policy violation unless the locale constraint 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
95% confidence
Finding

The instruction says to output Chinese by default whenever the user works in Chinese. Under the policy criteria, forcing a language behavior without explicit opt-in can be a locale/language policy violation unless the skill offers a choice or clearly justifies the constraint.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
85% confidence
Finding

The file provides a Chinese source-reference module as part of the workflow, but does not say to use it only when the user requests Chinese or chooses that locale. This can conflict with language-choice policy because it introduces a specific language option without explicit opt-in guidance.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
83% confidence
Finding

The markdown presents a Chinese version of prompt additions, but does not clarify that it should be used only for Chinese-speaking users or upon request. Without an explicit language-selection condition, the skill risks forcing or defaulting to a locale without user opt-in.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.