ClawHub
Back to skill

Security audit

定时早报生成

Security checks for vulnerabilities and agentic risk

Overview

This skill openly generates scheduled news briefings and sends them to a configured Feishu chat, with no evidence of hidden or unrelated behavior.

Install only if you want generated briefings posted to Feishu. Before enabling scheduling, confirm the target chat, posting time, how to disable it, and whether 30-day deduplication history or any personalization data is stored.

SkillSpector

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 (2)

Missing User Warnings

Medium
Confidence
88% confidence
Finding
The skill advertises automatic scheduled pushes to Feishu, which implies outbound transmission of generated content and possibly user-configured preferences to a third-party messaging platform, but it does not disclose what data is sent, when it is sent, or any consent/privacy implications. In a scheduling context, silent recurring delivery increases risk because users may enable continuous data sharing without understanding retention, recipients, or whether news summaries could include sensitive prompts or personalized content.

Missing User Warnings

Medium
Confidence
90% confidence
Finding
The handler automatically sends generated briefing content to a configured Feishu chat whenever `feishu_chat_id` is present, with no per-request confirmation, visibility, or authorization check in this file. That creates a data-flow risk where user-supplied or model-generated content may be exfiltrated to an external messaging channel unintentionally, especially if the skill is invoked in contexts where users do not expect outbound transmission.

Static analysis

No suspicious patterns detected.