Security audit

feishu-group-manager

Security checks across malware telemetry and agentic risk

Overview

This skill appears intended for Feishu group administration, but it can change shared chat settings and permissions while leaving key authorization and safety details under-documented.

Review before installing. Use only with a least-privilege Feishu app and approved chat IDs, verify the missing feishu-common helper before providing credentials, and require explicit confirmation before any group name, description, @all, invite, or edit-permission change.

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 (2)

Missing User Warnings

Medium

Confidence: 90% confidence
Finding: The skill explicitly supports changing Feishu group names, descriptions, and permission settings, which are administrative actions that can affect many users and alter access/control within a chat. The documentation provides direct invocation details but no warning, confirmation requirement, authorization guidance, or scope limitation, increasing the risk of accidental or unauthorized impactful changes by an agent.

Missing User Warnings

Medium

Confidence: 93% confidence
Finding: This code performs an external state-changing action by renaming a Feishu chat through the API without any confirmation, dry-run mode, or explicit warning at execution time. In an agent or automation context, this can cause unintended modifications to shared resources, misleading status signaling, and operational confusion if triggered accidentally or with the wrong chat ID.

VirusTotal

No VirusTotal findings

View on VirusTotal