ClawHub
Back to skill

Security audit

wacai-zhishudashi-baidu-ranking

Security checks across malware telemetry and agentic risk

Overview

This skill does what it says, but it sends data to a built-in WeCom webhook and includes that webhook secret in the artifacts.

Review before installing. Use only if you are comfortable with scraped titles, or any text passed to the helper, being sent to the embedded WeCom webhook. Prefer a version that removes the hard-coded webhook, rotates the exposed key, requires your own webhook via an environment variable or secret, supports dry-run/preview by default, and asks before sending.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
  • 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)

Context-Inappropriate Capability

Medium
Confidence
99% confidence
Finding
The script embeds a live WeCom webhook secret directly in source code, which is effectively a credential for posting to an external corporate channel. Anyone with access to the code can reuse that webhook to send arbitrary messages, spam the channel, or abuse it as an exfiltration endpoint, and the skill’s purpose of automated outbound posting makes this more dangerous rather than less.

Missing User Warnings

Medium
Confidence
91% confidence
Finding
The workflow sends scraped results to an external WeCom webhook without a clear warning that data leaves the local/browser context and is transmitted to a third-party endpoint. Even if the scraped content seems low sensitivity, silent transmission creates privacy, compliance, and misuse risks, especially if the skill is repurposed to send other text.

VirusTotal

66/66 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.