Back to skill

Security audit

Xiao Chuang You Objects

Security checks for vulnerabilities and agentic risk

Overview

This is a small Chinese-language lifestyle recommendation skill with no code execution, persistence, credential access, or hidden data flows.

Installers should expect a Chinese-language recommendation assistant for household objects and incense. Consider narrowing its trigger words and adding a user-language fallback, but no security-sensitive capability was found in the reviewed artifact.

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
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • 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
91% confidence
Finding

The skill metadata and behavior are written to assume Chinese-language interaction without stating any fallback or adaptation to user preference. This can produce exclusionary or mismatched responses when the broader system or user is operating in another language, reducing reliability and potentially causing users to miss important safety or product-use guidance.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
96% confidence
Finding

The activation keyword list includes very generic terms such as “香”, “买”, and “购”, which are likely to appear in many unrelated conversations. This can cause unintentional skill activation, leading to prompt-routing errors, inappropriate responses, or interference with other higher-priority skills. In this context the issue is operational rather than directly exploitative, but broad triggers increase the attack surface for prompt steering and accidental invocation.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
88% confidence
Finding

The reply specification mandates a fixed Chinese interaction hook and fixed response structure without allowing language or locale adaptation. In multilingual deployments this can cause the assistant to ignore user preference, degrade comprehension, and create confusion around product recommendations or usage cautions.

Content

No source excerpt is available for this finding.