ClawHub
Back to skill

Security audit

feishu-task-management-skill

Security checks across malware telemetry and agentic risk

Overview

The skill does what it claims, but it ships with Feishu credentials, a user token, and cached member data that should not be bundled in a public installable skill.

Review before installing. Do not use the bundled runtime config as-is; clear or replace it with your own Feishu app credentials, and the publisher should rotate the exposed app secret/token and remove cached member data from the package. Install only if you are comfortable granting the agent authority to modify Feishu tasks and manage task members through the configured account.

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
93% confidence
Finding
The skill instructs the agent to run local Python scripts that can read and write configuration files, access environment-backed credentials, and make network requests to Feishu APIs, yet the skill declares no permissions. This creates a transparency and governance gap: users and enforcement systems may not realize the skill can modify local state, use stored secrets, and perform external actions on tasks, increasing the risk of unintended data access or state-changing operations.

VirusTotal

65/65 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.