ClawHub
Back to skill

Security audit

企查查中转站

Security checks across malware telemetry and agentic risk

Overview

This is a disclosed business-data connector that sends queries and an AppKey to a remote zqcc service; it appears purpose-aligned but should be used carefully with sensitive data and credentials.

Install only if you intend to use the zqcc/Qichacha remote service. Keep ZQCC_APP_KEY out of chats, logs, screenshots, and repositories; do not override ZQCC_BASE_URL unless you control and trust the endpoint; and avoid submitting secrets or unnecessary personal data. Make sure you have a legitimate basis to query or share contact, legal, tax, executive, and risk records.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
Findings (5)

Missing User Warnings

Medium
Confidence
92% confidence
Finding
The documentation notes that the server retains recent history by AppKey and session ID, but it does not present this as a prominent privacy warning before users submit potentially sensitive enterprise queries. In a skill that handles business, contact, risk, and historical data, unclear retention notice can lead users to disclose regulated, confidential, or personal information without informed consent.

Missing User Warnings

Medium
Confidence
92% confidence
Finding
The catalog advertises broad access to sensitive enterprise and personal-risk data, including contact details, legal records, tax issues, executive profiles, and historical risk information, but provides no visible notice about lawful basis, authorization, privacy constraints, or acceptable use. In a skill whose purpose is to broker enterprise intelligence queries, this omission materially increases the chance of unauthorized or non-compliant data access and downstream privacy misuse.

Missing User Warnings

Medium
Confidence
92% confidence
Finding
The script sends arbitrary user-supplied messages and tool arguments, along with a bearer app key, to a remote third-party service endpoint. In the context of an agent skill, this is security-relevant because users may not realize their prompts, business data, or credentials are being transmitted off-box to an external host, which can expose sensitive information or enable misuse if the service is untrusted or compromised.

Missing User Warnings

High
Confidence
98% confidence
Finding
The config command prints a ready-to-use Authorization header containing the live bearer app key directly to stdout. This is dangerous because shell output is often logged, copied into chat, captured in terminal history, or exposed through tooling, leading to credential disclosure and unauthorized use of the associated account or API access.

External Transmission

Medium
Category
Data Exfiltration
Content
local url="$1"
  local body="$2"

  curl --fail-with-body --silent --show-error \
    --connect-timeout 15 \
    --max-time 300 \
    -X POST "$url" \
Confidence
90% confidence
Finding
curl --fail-with-body --silent --show-error \ --connect-timeout 15 \ --max-time 300 \ -X POST "$url" \ -H "Authorization: Bearer ${ZQCC_APP_KEY}" \ -H 'Content-Type: application/js

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.