Feishu Requirement Manager

Security checks across malware telemetry and agentic risk

Overview

This Feishu requirement-management skill is mostly purpose-aligned, but it can create or update workspace records and reuse shared stored table identifiers without clear confirmation or scoping.

Review before installing. Use it only with a Feishu account where the agent is allowed to create tables and modify requirement/task records, require confirmation before setup or updates, and consider changing the shared memory location to something scoped to the current user or workspace.

SkillSpector

By NVIDIA

Vulnerability Patterns

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

Findings (2)

Vague Triggers

Medium

Confidence: 89% confidence
Finding: The trigger keywords include broad, common phrases such as '查看进度' and '添加任务' that can appear in normal conversation outside the intended Feishu requirement-management context. This increases the chance of unintended skill invocation, which could cause the agent to create or modify requirement/task records without the user explicitly selecting this skill.

Missing User Warnings

Medium

Confidence: 91% confidence
Finding: The examples instruct the agent to create Feishu tables, create and update external records, and persist identifiers in a shared memory file without any explicit confirmation, warning, or consent flow. In an agent skill, this can normalize silent state-changing actions and cross-session persistence, increasing the risk of unintended data creation, modification, and leakage of app/table identifiers through shared memory.

VirusTotal

66/66 vendors flagged this skill as clean.

View on VirusTotal