ClawHub
Back to skill

Security audit

每日英语诗歌推送

Security checks across malware telemetry and agentic risk

Overview

This skill is a disclosed daily poem-to-Feishu notifier, and the reviewed files do not show hidden data access, credential theft, or destructive behavior.

Install this only if you want daily poem content posted to Feishu. Configure the Feishu destination and credentials yourself, and avoid using it in chats where private prompts or sensitive business data could be included in the generated message.

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 (1)

Missing User Warnings

Medium
Confidence
90% confidence
Finding
The skill exfiltrates fetched and generated content to an external messaging platform using the `message` tool, but does not present any user-facing notice, consent step, or destination scoping beyond `channel: feishu`. Even though the intended data is poem content, external delivery creates a real data-handling risk if fetched content, prompts, or unexpected context are included in the outbound message.

VirusTotal

65/65 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.