ClawHub
Back to skill

Security audit

Phy Xiaohongshu Gtm

Security checks for vulnerabilities and agentic risk

Overview

This is a marketing-content guidance skill with no code execution, installation, persistence, or credential access, though users should notice its broad activation and Chinese-output preference.

Install this if you want a Xiaohongshu-focused content strategy helper. Expect it to encourage web research of public social content and to default strongly toward Chinese-language marketing output; review generated advice before using it for brand or platform-compliance decisions.

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
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (2)

Vague Triggers

Medium
Confidence
95% confidence
Finding
The trigger description is overly broad because it activates on generic phrases like any 小红书 planning, Xiaohongshu marketing, and cross-border ecommerce content. This can cause the skill to be invoked outside its intended scope, overriding user intent or injecting prescriptive behavior into unrelated conversations, which is a prompt-safety and control-boundary issue.

Natural-Language Policy Violations

Medium
Confidence
97% confidence
Finding
The skill mandates all-Chinese output without allowing for the user's language preference, which can reduce transparency, impair user review, and create opportunities for misalignment if the user operates in another language. While not directly enabling code execution or data exfiltration, it weakens user control and can make unsafe or unwanted content harder for some users to evaluate.

Static analysis

No suspicious patterns detected.