Back to skill

Security audit

Weather Plus

Security checks for vulnerabilities and agentic risk

Overview

This is a straightforward weather-query skill that discloses its public weather data sources and does not include executable code, persistence, credentials, or privileged local access.

Install if you want a Chinese-language weather helper that queries public weather APIs. Be aware that location queries may be sent to wttr.in or Open-Meteo, and the skill does not clearly define non-weather activation boundaries or multilingual behavior.

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
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
92% confidence
Finding

The skill description is broadly framed around common weather questions, which can overlap with ordinary conversation and cause unintended activation. In an agent environment, overbroad triggering can route unrelated user input into this skill, leading to incorrect tool use, privacy leakage in downstream requests, or degraded assistant behavior.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
85% confidence
Finding

整个技能文档均以中文描述输入输出示例和行为预期,但未说明是否支持其他语言,也未向用户提供语言/locale 选择。这可能构成语言/地区策略上的默认强制约束,特别是该技能宣称支持“全球城市天气信息”。

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
91% confidence
Finding

The example utterances are very generic everyday phrases like asking how the weather is or how many degrees it is, without clear activation constraints. This increases the chance of false positives and accidental invocation, especially in multilingual or context-rich chats where similar phrases may appear incidentally.

Content

No source excerpt is available for this finding.

Vague Triggers

Low
Category
Not specified by scanner
Confidence
84% confidence
Finding

This manifest file gives a broad natural-language description of the skill's capabilities but does not specify what phrases or conditions should activate it. Without explicit trigger scope or exclusion conditions, invocation logic may be inferred too broadly from common weather-related requests.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.