Back to skill

Security audit

Xiao Chuang You Season

Security checks for vulnerabilities and agentic risk

Overview

This is a small Chinese seasonal-customs guidance skill with no code execution, persistence, credential use, or hidden data handling.

This skill is safe to install from a security perspective. Users should expect Chinese-language responses focused on Chinese seasonal customs, and maintainers may want to narrow activation rules or add language fallback guidance to avoid irrelevant routing.

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
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 (3)

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
83% confidence
Finding

The skill is written to operate in Chinese and implicitly constrains responses to Chinese without stating a user-language fallback. In a broader assistant environment, this can lead to inaccessible or confusing output for users who ask in another language, reducing reliability and potentially bypassing user preference handling.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
93% confidence
Finding

The activation description is broad enough that the skill may trigger on loosely related queries about dates, holidays, or seasonal topics, causing unintended routing. Over-broad activation can interfere with correct skill selection and produce irrelevant or policy-inconsistent responses, though this file does not show direct data exfiltration or code-execution risk.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The trigger list contains generic terms like '节日' and '春节' without scope constraints, which can overlap with ordinary conversation and cause accidental activation. This increases the chance of misrouting user requests and can crowd out more appropriate skills, especially in multilingual or general-assistant contexts.

Content

No source excerpt is available for this finding.