Back to skill

Security audit

Xiao Chuang You Garden

Security checks for vulnerabilities and agentic risk

Overview

This is a gardening advice skill with no code execution, persistence, credential access, or unrelated behavior.

Before installing, note that the skill may activate on broad plant or balcony terms; otherwise it appears limited to benign gardening guidance and does not ask for sensitive access.

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 (2)

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The description activates on broad gardening-related themes such as 园艺、种花、阳台、花草、绿植、盆栽、花期, which can appear in ordinary conversation without an explicit request to invoke a specialized skill. This can cause unintended routing or over-triggering, reducing reliability and potentially exposing users to irrelevant skill behavior when the base assistant would be more appropriate.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
97% confidence
Finding

The trigger list contains many generic single-word activators, including common nouns like 阳台、花草、浇水、盆栽、绿植, that may occur in normal conversation outside deliberate skill use. In a routing system, such vague triggers increase the chance of false activations, which can hijack unrelated conversations and degrade system behavior more than the broad description alone.

Content

No source excerpt is available for this finding.