Back to skill

Security audit

Trip plan to WeChat

Security checks for vulnerabilities and agentic risk

Overview

This skill is a coherent travel-itinerary sharing wrapper that publishes user-approved trip content to a WeChat-friendly LivePage link, with some privacy considerations users should understand.

Install this if you want an agent to publish confirmed trip materials to a hosted WeChat-friendly page. Before using forms or engagement summaries, make sure companions understand that votes, sign-ups, comments, and viewing activity may be visible to the trip organizer, and prefer passcode visibility over public sharing.

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 trigger phrases are broad enough to match ordinary travel-related conversation rather than an explicit request to publish content. That can cause unintended invocation of a skill that shares information externally, increasing the risk of accidental disclosure of itinerary details, links, or companion coordination data.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
84% confidence
Finding

The skill instructs the agent to share trip pages and later read engagement, voting, and feedback data, but it does not require a clear user-facing privacy notice about what companion data may be collected or visible. In a travel-sharing context, this can expose sensitive behavioral information such as who viewed the page, participation choices, and possibly travel timing or social relationships without informed consent.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.