Back to skill

Security audit

China

Security checks for vulnerabilities and agentic risk

Overview

This is a China travel-planning skill with disclosed local trip memory and no evidence of hidden network, executable, or system-level behavior.

Before installing, understand that the skill may save travel preferences and trip details locally in ~/china/memory.md and reuse them later; review or delete that file if you do not want persistent travel memory.

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 (4)

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
94% confidence
Finding

The trigger condition 'When user mentions China travel for the first time' is broad and underspecified, which can cause the skill to activate on casual or exploratory mentions rather than clear user intent to use the skill. In this file, that matters because activation immediately leads into filesystem actions and persistent memory setup, increasing the chance of unintended data handling.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
97% confidence
Finding

The skill instructs the agent to create and update files under ~/china and to read them silently on return visits, without any user-facing disclosure or consent flow. This creates a privacy and transparency risk because user travel preferences, constraints, and potentially sensitive data can be persisted and reused without the user clearly understanding that local memory is being created and read.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
85% confidence
Finding

The document is explicitly scoped to 'China' in the title, which imposes a locale-specific framing without any nearby note that this is optional, user-selected, or part of a clearly documented regional compliance context. Under the policy criteria, locale constraints should be opt-in or explicitly justified.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
82% confidence
Finding

The skill is explicitly constrained to China in the title and all guidance is framed only around Chinese regions, with no indication that this locale restriction is optional or user-selected. The policy allows locale constraints when they are clearly justified, but this file does not explain why China-only guidance is required.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.