ClawHub
Back to skill

Security audit

Z视介频道直播

Security checks for vulnerabilities and agentic risk

Overview

This skill does what it says: it maps Zhejiang TV channel names to fixed Z视介 live links and may open one in the browser.

Install only if you want an agent to resolve and open Z视介 live TV channel pages. Be aware that it may open your default browser automatically; use or request --no-open when you only want the link or Markdown response.

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
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • Behavioral ASTexec() Call, eval() Call, Dynamic Import
  • MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
Findings (6)

Undeclared Tool Scope

Medium
Category
MCP Least Privilege
Confidence
87% confidence
Finding

The skill invokes shell-based execution (python3 scripts/zshijie_live.py ...) and attempts to open a browser, but it does not declare any permissions or allowed-tools scope. This creates an authorization gap where an agent may run code or launch external resources without explicit least-privilege constraints, increasing the risk of unintended command execution or environment interaction if the skill or its dependencies are modified or abused.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
90% confidence
Finding

The alias mapping accepts very broad, ambiguous phrases such as '卫视', '国际', and numeric colloquialisms like '6频道/六频道' and instructs the agent to directly open a live channel when such phrases appear. This can cause unintended activation or misrouting from ordinary conversation context, especially because the skill's purpose is to generate/open a URL immediately rather than ask for clarification when intent is uncertain.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
97% confidence
Finding

The script is configured to open the resolved URL in the user's default browser by default, which creates an external side effect without explicit confirmation at runtime. In an agent/skill context, this can cause unwanted navigation, leak user context to a third-party site, and make phishing or drive-by redirection risks more serious if the URL-generation logic is ever expanded or modified.

Content

No source excerpt is available for this finding.

subprocess module call

Medium
Category
Dangerous Code Execution
Confidence
70% confidence
Finding

subprocess module calls execute external commands. Without careful input validation, this enables command injection.

Content

Scanner excerpt · scripts/zshijie_live.py (reported line 256)May include surrounding context.

python
return

    try:
        subprocess.run(
            cmd,
            check=False,
            stdout=subprocess.DEVNULL,

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
93% confidence
Finding

The default prompt explicitly instructs the skill to 'Return a short Markdown card' in English while the skill name and examples are in Chinese, with no opt-in or user choice for language. This creates a natural-language locale policy issue because the skill appears to impose a language preference rather than adapting to or asking for the user's preferred language.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
88% confidence
Finding

Natural-language descriptions, aliases, output headings, and help examples are all fixed to Chinese-language usage, which can impose a locale preference on users without opt-in. The file does not indicate that the skill is intentionally limited to a Chinese-speaking or region-specific audience.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.