ClawHub

Zhipu Search

Security checks across malware telemetry and agentic risk

Overview

This skill does what it claims: it sends user search queries to Zhipu's web search API using a declared API key, with no hidden persistence or unrelated access found.

Install only if you trust Zhipu with the search terms you submit. Use a limited-scope API key, avoid shared machines or shell startup files for long-lived secrets, and do not send confidential prompts, credentials, personal data, or internal business content as search queries.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (2)

Vague Triggers

Medium
Confidence
81% confidence
Finding
The skill's trigger guidance is very broad (`search for`, `look up`, `latest news`) and lacks exclusion boundaries, which can cause over-selection for many generic user requests. In an agent environment, that increases the chance of unnecessary external calls and transmission of user queries to a third-party service when a local answer or different skill would have been more appropriate.

External Transmission

Medium
Category
Data Exfiltration
Content
```bash
export ZHIPU_API_KEY="your_key"

curl -s -X POST "https://open.bigmodel.cn/api/paas/v4/chat/completions" \
  -H "Authorization: Bearer $ZHIPU_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
Confidence
91% confidence
Finding
curl -s -X POST "https://open.bigmodel.cn/api/paas/v4/chat/completions" \ -H "Authorization: Bearer $ZHIPU_API_KEY" \ -H "Content-Type: application/json" \ -d

VirusTotal

65/65 vendors flagged this skill as clean.

View on VirusTotal