Back to skill

Security audit

灵途-旅行规划助手

Security checks for vulnerabilities and agentic risk

Overview

This travel-planning skill is mostly coherent, but it asks users to share API keys in chat and understates when location data may be sent to map/weather providers.

Review this skill before installing. It is not showing destructive or attacker-directed behavior, but you should avoid pasting API keys into ordinary chat unless you understand how the platform stores and exposes them. Also note that nearby-search features may send your provided location or coordinates to map services despite the data-flow text emphasizing destination names only.

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
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
Findings (6)

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
96% confidence
Finding

The skill advertises extremely broad trigger phrases covering most travel-related conversation, which can cause unintended invocation in contexts where the user did not explicitly request this skill. Over-broad activation increases the chance that the skill’s rigid workflow, third-party data-sharing prompts, and external lookups are initiated unnecessarily, creating consent, privacy, and reliability risks.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
91% confidence
Finding

The skill content is entirely written to enforce Chinese interaction and does not provide a language-negotiation step, which can cause users to misunderstand consent prompts, itinerary details, or safety-critical travel information. In a travel assistant, language mismatch can directly affect bookings, dates, transport choices, and third-party data-sharing authorization, making the issue more than a mere UX defect.

Content

No source excerpt is available for this finding.

Context-Inappropriate Capability

Medium
Category
Not specified by scanner
Confidence
97% confidence
Finding

The guide explicitly instructs users to paste third-party API credentials into the chat and states the assistant will save them to memory or via a secret-edit mechanism. Even if intended for legitimate feature enablement, collecting and storing secrets inside a conversational skill expands the credential exposure surface and is not strictly necessary for a travel-planning workflow from the user's perspective.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
98% confidence
Finding

The documentation tells users to send full API host/key values directly in chat but provides no warning that these are sensitive secrets that should not be exposed in conversational history. This creates a realistic risk of inadvertent disclosure through logs, transcripts, downstream tooling, or unauthorized access to stored chat context.

Content

No source excerpt is available for this finding.

Ssd 3

Medium
Category
Not specified by scanner
Confidence
98% confidence
Finding

The natural-language setup instruction includes a ready-made template for users to paste API secrets, normalizing unsafe handling of credentials in the conversation itself. In the context of a travel planner, this is more dangerous because secret collection is ancillary to the core function and may condition non-technical users to disclose credentials without understanding the security implications.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
87% confidence
Finding

This markdown file contains user-facing natural-language content that implicitly forces a specific language/locale. Under the policy, language constraints should either be optional for the user or clearly justified as region-specific; neither is stated here.

Content

No source excerpt is available for this finding.