ClawHub
Back to skill

Security audit

小觉

Security checks for vulnerabilities and agentic risk

Overview

This is a simple Chinese-language Buddhist dialogue persona skill with no code, tools, persistence, or data-access behavior.

Install this if you want a concise Chinese Buddhist-dialogue persona. Be aware it may activate somewhat broadly for reflective conversation, but it does not include code execution, data access, persistence, or external calls.

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

Vague Triggers

Medium
Confidence
86% confidence
Finding
The description says the skill is '用于佛法讨论、当下对话', which describes a very broad conversational scope without clear activation boundaries or explicit trigger phrases. This ambiguity could cause the skill to match generic day-to-day conversation, especially '当下对话', rather than a narrowly defined domain-specific invocation.

Natural-Language Policy Violations

Medium
Confidence
88% confidence
Finding
The skill content and persona are entirely specified in Chinese, and the description presents the assistant's behavior in that language without any indication that users may choose another language. Under the stated policy, forcing a specific language without opt-in can be a natural-language policy violation unless the locale restriction is clearly justified.

Static analysis

No suspicious patterns detected.