ClawHub
Back to skill

Security audit

Toutiao Hot News CN | 今日头条热榜

Security checks for vulnerabilities and agentic risk

Overview

This skill is a straightforward public Toutiao hot-news fetcher with no hidden local access or persistence, though its trigger wording and command examples should be tightened.

Install only if you want agents to query Toutiao for Chinese hot-news rankings. Be aware that broad trigger terms may invoke it for general trend/news prompts, and the documented command path appears to need correction from scripts/toutiao.js to scripts/toutiao.cjs.

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 (2)

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
96% confidence
Finding

The skill description includes very broad trigger phrases such as “头条”, “热榜”, “中国新闻”, “China news”, and especially “trending”, which can match many ordinary user requests beyond the intended Toutiao-specific scope. This can cause the agent to invoke the skill in irrelevant contexts, leading to incorrect tool selection, unnecessary external requests, and reduced reliability; while not a direct code-execution flaw, it is a genuine security/control issue in agent routing.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
91% confidence
Finding

Line L030 forces requests to prefer the zh-CN locale, which is a natural-language locale choice embedded in code. The file does not offer a user opt-in or configuration mechanism for language selection, and no region-specific justification is documented in the file.

Content

No source excerpt is available for this finding.