飞书读取云文档

Security checks across malware telemetry and agentic risk

Overview

This skill is a non-executable Feishu/Lark document helper whose behavior is disclosed and aligned with fetching document content and related media.

Install only if you intend your agent to retrieve Feishu/Lark document content. Use it with explicit document or wiki links/tokens, keep Feishu permissions least-privilege, and choose media download paths carefully because document text and attachments may contain sensitive business data.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (1)

Vague Triggers

Low
Confidence
84% confidence
Finding
The manifest description is broad enough that an orchestrator could invoke this skill for loosely related requests about Feishu documents without clear boundaries such as read-only scope, supported document types, or required user intent. In this skill, the danger is limited because the documented behavior is content retrieval rather than code execution, but over-broad routing can still cause unintended access to enterprise document contents or unnecessary exposure of sensitive data.

VirusTotal

65/65 vendors flagged this skill as clean.

View on VirusTotal