ClawHub
Back to skill

Security audit

Feishu Doc Summarizer

Security checks across malware telemetry and agentic risk

Overview

This skill appears to do the expected job of reading Feishu/Lark documents to summarize them, with no evidence of hidden execution, exfiltration, or destructive behavior.

Install only if you intend the agent to read Feishu/Lark documents you ask it to summarize. Avoid using it on documents you are not authorized to access, and treat summaries of sensitive business or personal documents as sensitive too.

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
92% confidence
Finding
The skill instructs the agent to read full Feishu/Lark document contents and additionally consult MEMORY.md to shape the response, but it provides no explicit user notice or consent boundary around handling potentially sensitive document data. This creates a real privacy and data-governance risk because users may not realize their cloud document contents will be fetched, processed, and combined with persistent memory-driven behavior.

VirusTotal

63/63 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.