ClawHub
Back to skill

Security audit

获取各大平台热榜

Security checks across malware telemetry and agentic risk

Overview

This is a read-only hot-list API documentation skill that contacts a disclosed third-party service and does not request credentials, local files, or mutation privileges.

Install this if you are comfortable with your agent contacting airouter.tech for public trending-topic lookups. For ambiguous news questions, configure your agent to confirm or narrow the platform first, and keep any scheduled polling or caching opt-in and rate-limited.

SkillSpector

By NVIDIA
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 (3)

Vague Triggers

Medium
Confidence
92% confidence
Finding
The guide encourages broad natural-language activation of the skill without defining clear invocation boundaries, which can cause the platform to call the skill for generic user requests that merely resemble hot-topic queries. This increases the chance of unintended external requests, data retrieval, and overbroad tool use when the user did not explicitly mean to invoke this specific skill.

Vague Triggers

Medium
Confidence
94% confidence
Finding
The text says the agent can obtain hot-rank data through natural language or direct API use, but it does not specify the limits of automatic invocation or fallback behavior for ambiguous prompts. In an agent environment, this ambiguity can lead to unnecessary third-party API calls and unintended disclosure of user intent to the external service.

Vague Triggers

Medium
Confidence
96% confidence
Finding
The example trigger "今天有什么热点新闻？" is extremely broad and overlaps with ordinary conversation, making accidental activation plausible in many benign chats. In a tool-enabled agent, such broad triggers can cause routine conversational prompts to generate external API traffic and responses the user did not specifically request from this service.

VirusTotal

66/66 vendors flagged this skill as clean.

View on VirusTotal