Back to skill

Security audit

weekend-escape

Security checks for vulnerabilities and agentic risk

Overview

This is a Chinese weekend travel-planning skill that uses disclosed flyai travel searches and does not include code, persistence, credential handling, or destructive behavior.

Install this if you want a Chinese-language weekend-trip planning assistant using flyai. Be aware that casual phrases about wanting to get away may trigger it, so users or routers should confirm vague requests before running travel searches that use location, dates, budget, or preferences.

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 (5)

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The skill metadata description uses broad, common phrases such as '周末去哪玩' and '想逃离城市' as activation cues, which can overlap with ordinary conversation and cause unintended invocation. This increases the chance the skill activates without clear user intent, potentially leading to unnecessary tool usage, irrelevant recommendations, or unexpected access to travel-search capabilities.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
91% confidence
Finding

The manifest description is entirely in Chinese and defines invocation phrases only in Chinese, which implies a fixed language expectation. The file does not state that the skill is China-specific or provide any user opt-in or alternative language handling, which is a natural-language locale policy concern.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
97% confidence
Finding

The trigger section lists several ambiguous examples like '想逃离城市' and '这周太累了,想出去透透气' without constraints, which are common lifestyle statements rather than explicit requests to invoke a travel-planning skill. In context, this can make the assistant route casual chat into the skill and trigger downstream searches for flights, hotels, and POIs that the user did not clearly ask for.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The invocation examples include very broad, everyday phrases like '周末去哪玩' and '想逃离城市', which can cause the skill to trigger in unrelated conversations and override more appropriate skills or routing logic. In an agent environment, overly generic triggers increase the chance of accidental activation, irrelevant recommendations, and unintended access to user context such as location, budget, or travel preferences.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
87% confidence
Finding

All user-facing descriptions and examples are presented only in Chinese, and the file does not indicate that users may interact in other languages or that the skill is intentionally restricted to a Chinese-language audience. This can violate language or locale policy when a skill implicitly forces one language without user opt-in.

Content

No source excerpt is available for this finding.