ClawHub
Back to skill

Security audit

新闻联播中翻中

Security checks for vulnerabilities and agentic risk

Overview

This skill is a coherent Chinese-language helper for fetching public CCTV Xinwenlianbo transcripts and translating official phrasing into plain Chinese, with no local execution, persistence, credentials, or destructive behavior found.

Install this if you want Chinese-language summaries and interpretation of Xinwenlianbo transcripts from public CCTV pages. Be aware that its trigger phrases are somewhat broad, so confirm intent when a request only loosely mentions "联播" or policy trends.

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
  • 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

Medium
Category
Not specified by scanner
Confidence
90% confidence
Finding

The trigger conditions are overly broad and include common conversational phrases such as asking about recent policy trends, which can cause the skill to activate in contexts the user did not specifically intend. Unintended activation is risky because this skill fetches external content and applies political/policy interpretation, potentially hijacking unrelated conversations or introducing unrequested external data into the session.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
92% confidence
Finding

The metadata description says to use the skill when the user merely 'references 新闻联播/新闻联播翻译/联播解读', which is broad enough to trigger on incidental mentions rather than an actual request to translate or summarize content. Overbroad activation can cause incorrect routing, unnecessary web fetching, and unintended transformation of user intent, especially because the skill performs external retrieval and interpretive analysis.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The 'When to Use' section includes ambiguous triggers such as '联播' and 'xwlb', which are shorthand terms that may appear in unrelated contexts and can cause accidental skill invocation. In this skill, mistaken invocation is more concerning because it may launch a multi-step workflow with web fetching, transcript extraction, and policy interpretation, leading to irrelevant external access and misleading outputs.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
88% confidence
Finding

This markdown file is entirely written in Chinese and presents the skill content in that language without any indication that users can choose another language or that the skill is intended only for a Chinese-speaking or region-specific audience. Under the policy rule, a forced language or locale without user opt-in is a natural-language policy concern.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.