ClawHub

宠物大全查询 - 聚合数据

Security checks across malware telemetry and agentic risk

Overview

This is a straightforward pet-information lookup skill that uses a disclosed Juhe API key and fixed Juhe API endpoints, with no evidence of hidden, destructive, or unrelated behavior.

Install only if you are comfortable using a Juhe API key for this skill. Use a dedicated, quota-limited key if possible, avoid putting sensitive personal context into pet search terms, and do not commit scripts/.env or paste the key into shared logs or command history.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (6)

Vague Triggers

Medium
Confidence
88% confidence
Finding
The description is broad enough that an agent may invoke the skill for loosely related pet questions without strong boundaries, increasing the chance of unnecessary third-party calls and unintended data sharing. In an agentic system, ambiguous triggering can become a security/privacy problem because user text may be sent externally when local answering would suffice.

Vague Triggers

Medium
Confidence
92% confidence
Finding
The AI usage guide says to act whenever the user asks about pet information, but it does not define when the skill should not be used, such as for medical advice, emergency care, general conversational questions, or sensitive user content. This ambiguity can cause over-broad activation and unnecessary transmission of user queries to the external API.

Missing User Warnings

Medium
Confidence
94% confidence
Finding
The skill states that it uses the Juhe API in real time, but it does not clearly warn that user query content will be sent to a third-party service. This creates a privacy and consent issue, especially because users may include personal context in natural-language pet questions.

Missing User Warnings

Medium
Confidence
92% confidence
Finding
The search request places the API key in the URL query string when calling the external juhe.cn API. Even over HTTPS, query strings are commonly exposed in logs, monitoring systems, browser/history equivalents, proxy infrastructure, and debugging output, so this increases the chance of credential disclosure without clearly warning the user that their key is sent off-box.

Missing User Warnings

Medium
Confidence
90% confidence
Finding
The detail lookup also transmits the API key in the URL query string to an external service, along with the queried pet identifier. This creates the same credential exposure risk through URL logging and infrastructure traces, and there is no explicit user-facing notice that the tool sends their key and query context to a third party.

Credential Access

High
Category
Privilege Escalation
Content
export JUHE_PET_QUERY_KEY=你的 AppKey

# 方式二：.env 文件（在脚本目录创建）
echo "JUHE_PET_QUERY_KEY=你的 AppKey" > scripts/.env

# 方式三：每次命令行传入
python scripts/pet_query.py --key 你的AppKey 哈士奇
Confidence
95% confidence
Finding
.env

VirusTotal

67/67 vendors flagged this skill as clean.

View on VirusTotal