飞书增强套件

Security checks across malware telemetry and agentic risk

Overview

This is a coherent Feishu automation helper, but it handles powerful Feishu app credentials and should be used with least-privilege scopes.

Install only if you trust the publisher and need Feishu automation. Use a least-privilege Feishu app, store FEISHU_APP_ID and FEISHU_APP_SECRET in a proper secret or environment mechanism instead of prompt-visible notes, and review recipients, table IDs, and payloads before sending messages or bulk-creating records.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
  • 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)

Lp3

Medium
Category
MCP Least Privilege
Confidence
94% confidence
Finding
The skill declares installation and use of shell-capable binaries (`curl`, `jq`) but does not declare corresponding permissions or clearly scope how shell/network execution is controlled. This creates an execution-capability gap where downstream agents may run external commands and make network requests without an explicit trust or permission boundary, increasing the risk of unintended data access or exfiltration.

VirusTotal

66/66 vendors flagged this skill as clean.

View on VirusTotal