Back to skill

Security audit

spontaneous trip planner

Security checks for vulnerabilities and agentic risk

Overview

This skill is a disclosed Chinese travel-planning helper that asks for trip preferences and uses travel search tools, with no evidence of hidden or destructive behavior.

Installers should know this skill may open a popup to ask for travel details and may send destination or preference queries to flyai travel tools. It is best suited for Chinese-language travel planning; users who only mention travel casually may want to confirm they actually want itinerary help before proceeding.

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

High
Category
Not specified by scanner
Confidence
98% confidence
Finding

The manifest description says the skill should auto-trigger whenever users mention broad travel-related topics like trips, sightseeing, attractions, or itinerary planning. This can cause the skill to activate in contexts where the user is only discussing travel casually, leading to unnecessary data collection via popup questions and tool use without sufficiently narrow intent gating.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
90% confidence
Finding

The manifest description and the full skill instructions are written to operate exclusively in Chinese, including fixed Chinese prompts and output structure, with no indication that users may choose another language. This creates a locale/language policy issue because the skill imposes a specific language without documented opt-in or justification.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
88% confidence
Finding

The usage section reinforces broad activation criteria, including general needs to query attractions, flights, hotels, or scenario-based recommendations, without requiring a clear planning request. In context, this broadens the chance of over-invocation and unnecessary collection of location and travel preference data, though it is less authoritative than the manifest trigger itself.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The prompts and expected outputs are entirely specified in Chinese and repeatedly prescribe Chinese-language response behavior and China-specific travel planning assumptions. For an all-file-types policy check, this indicates a language/locale constraint without offering the user a choice or documenting a justified regional limitation.

Content

No source excerpt is available for this finding.