ClawHub
Back to skill

Security audit

Phy Creative Image

Security checks for vulnerabilities and agentic risk

Overview

This skill is a markdown-only guide for creating branded image-generation prompts and does not request sensitive access, execution, persistence, or hidden authority.

Install this if you want CanMarket-specific image prompt templates and brand rules. Review the examples to make sure the brand style, platform choices, and output language match your audience, but the artifact does not show risky local access or automatic execution.

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
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • 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 (2)

Natural-Language Policy Violations

Low
Confidence
83% confidence
Finding
The example for a Chinese user request produces an English-language output label and prompt text ("Xiaohongshu cover image for CES preparation checklist post."), which suggests the skill may default to English phrasing even when the user's request is in Chinese. This is a mild language-policy concern because the file does not explicitly state that users can choose their preferred output language.

Natural-Language Policy Violations

Low
Confidence
84% confidence
Finding
The section heading and prompt text explicitly target '小红书' and use Chinese-language context, which can be interpreted as forcing a specific locale/platform convention in a general prompt examples file. The file does not indicate that this locale choice is optional, user-selected, or limited to region-specific use cases.

Static analysis

No suspicious patterns detected.