ClawHub
Back to skill

Security audit

雪球网信息获取

Security checks across malware telemetry and agentic risk

Overview

The skill is a coherent Xueqiu data API helper, but it asks users to put live paid API credentials into chat and relies on a third-party service without enough secret-handling guidance.

Review before installing. Use only credentials you are comfortable exposing to the agent environment, prefer a low-balance or revocable key, rotate the key if it was pasted into chat, and avoid submitting sensitive investment research queries unless you trust wxpub.aibana.art and its data handling.

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 (3)

Missing User Warnings

High
Confidence
97% confidence
Finding
The README explicitly instructs users to paste live `app_id` and `secure_key` into the chat with the model, which encourages disclosure of active credentials through a conversational channel that may be logged, retained, exposed to plugins/tools, or visible to operators. In a skill ecosystem, this is especially dangerous because the model may subsequently reuse or reveal those secrets in prompts, tool calls, traces, or error messages.

Missing User Warnings

Medium
Confidence
93% confidence
Finding
The skill instructs users to provide `app_id`, `secure_key`, and query data to a non-first-party remote service, but it does not clearly warn that these credentials and request contents are transmitted to `https://wxpub.aibana.art` (and locally to `http://localhost:8080/...`). In an agent setting, lack of explicit disclosure can mislead users into sharing secrets or sensitive investment-research queries with a third party, increasing privacy, credential exposure, and trust-boundary risks.

Ssd 3

Medium
Confidence
95% confidence
Finding
Telling users to provide live credentials directly to the model creates unnecessary secret-handling risk, because chat transcripts are not an appropriate secret management channel and may be stored or processed beyond the user's immediate intent. The skill context increases risk because successful API calls require those credentials, so users are being nudged toward unsafe behavior as part of normal setup.

VirusTotal

VirusTotal findings are pending for this skill version.

View on VirusTotal

Static analysis

No suspicious patterns detected.