ClawHub
Back to skill

Security audit

北京环球影城游园助手

Security checks for vulnerabilities and agentic risk

Overview

This is a coherent Beijing Universal Studios trip-planning skill that uses fixed public theme-park API endpoints for live park data and local preset data for recommendations.

Installers should understand that live wait times and schedules require contacting themeparks.wiki, which may reveal normal request metadata such as IP address and User-Agent to that service. Ticket prices and some recommendations are local preset guidance and should be verified with official park channels before purchase or travel decisions.

A.I.G

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

SkillSpector

Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • YARA SignaturesMalware Match, Webshell Match, Cryptominer Match
  • MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
  • MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
Findings (7)

YARA rule 'agent_skill_mcp_tool_poisoning_metadata': MCP/tool metadata poisoning indicators in tool schemas or skill manifests [agent_skills]

High
Category
YARA Match
Confidence
80% confidence
Finding

YARA rule matched a hack tool or exploit indicator (offensive tools, reconnaissance, privilege escalation, or exploit frameworks).

Content

Scanner excerpt · scripts/universal_beijing.py (reported line 32)May include surrounding context.

python
"name_en": "Harry Potter and the Forbidden Journey™",
        "name_cn": "哈利·波特与禁忌之旅",
        "area": "哈利·波特的魔法世界",
        "lat": 39.8555, "lng": 116.6765,
        "height_min_cm": 122, "thrill_level": 5, "age_min": 8, "duration_min": 5,
        "tags": ["刺激", "室内", "4D沉浸", "魔法"],
        "popularity": 5, "is_indoor": True,
        "description": "骑上魔法扫帚穿越霍格沃茨，全球最热门项目之一",
        "good_for_kids": False, "good_for_teens": True, "good_for_elderly": False,
    },
    {
        "id": "e6ea7bbf-92ca-414a-8112-c473c20f04c3",
        "name_en": "Decepticoaster",
        "name_cn": "霸天虎过山车",
        "area": "变形金刚基地",
        "lat": 39.8545, "lng": 116.6795,
        "height_min_cm": 132, "thrill_level": 5, "age_min": 10, "duration_min": 2,
        "tags": ["刺激", "室外", "过山车", "极速"],
        "popularity": 5, "is_indoor": False,
        "descriptio

Undeclared Tool Scope

Medium
Category
MCP Least Privilege
Confidence
94% confidence
Finding

The skill declares multiple tools that rely on external real-time data and explicitly states that wait times and operating hours are fetched from a public API, but it does not define any tool scope such as permissions or allowed-tools. This creates an overbroad trust boundary: the runtime may permit network-capable behavior without an explicit least-privilege declaration, making review and enforcement harder.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The file's descriptive text, usage strings, and all user-facing outputs are written exclusively in Chinese, presenting the skill as Chinese-only with no mechanism to choose another language. Under the policy, forcing a specific language without user opt-in is a natural-language policy violation.

Content

No source excerpt is available for this finding.

External Transmission

Medium
Category
Data Exfiltration
Confidence
60% confidence
Finding

Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.

Content

Scanner excerpt · scripts/universal_beijing.py (reported line 458)May include surrounding context.

python
def fetch_live_data():
    """获取实时排队数据"""
    url = f"https://api.themeparks.wiki/v1/entity/{PARK_ID}/live"
    try:
        req = urllib.request.Request(url, headers={"User-Agent": "UniversalBeijingSkill/1.0"})
        with urllib.request.urlopen(req, timeout=30) as resp:

External Transmission

Medium
Category
Data Exfiltration
Confidence
60% confidence
Finding

Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.

Content

Scanner excerpt · scripts/universal_beijing.py (reported line 492)May include surrounding context.

python
def fetch_live_data():
    """获取实时排队数据"""
    url = f"https://api.themeparks.wiki/v1/entity/{PARK_ID}/live"
    try:
        req = urllib.request.Request(url, headers={"User-Agent": "UniversalBeijingSkill/1.0"})
        with urllib.request.urlopen(req, timeout=30) as resp:

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
90% confidence
Finding

This skill’s natural-language interface, examples, and usage guidance are all presented in Chinese, which effectively forces a specific language/locale on users. The file does not state that the skill is intended only for Chinese-speaking users or offer any opt-in or alternative language behavior.

Content

No source excerpt is available for this finding.

Missing User Warnings

Low
Category
Not specified by scanner
Confidence
87% confidence
Finding

The skill fetches live queue and schedule data from a third-party API using urllib, but the runtime path contains no print/log message or prompt informing the user that network access will occur. For code files, outbound network calls should have some visible disclosure unless clearly covered elsewhere; this file's code comments/docstrings are internal and not user-facing.

Content

No source excerpt is available for this finding.