ClawHub

飞书需求整理

Security checks across malware telemetry and agentic risk

Overview

This skill’s Feishu document reading and document creation behavior matches its stated purpose, but users should review sensitive content and sharing permissions before use.

Install this only if you are comfortable having the agent process the Feishu links, meeting notes, or pasted records you provide. Before running it on sensitive customer or internal material, confirm you have permission to process that content, review the generated document, and check exactly who receives Feishu access, especially edit permission.

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
93% confidence
Finding
The skill is designed to ingest communication records from Feishu docs, meeting minutes, and pasted text, which commonly contain sensitive business and personal data, yet it provides no user-facing notice, consent checkpoint, or data-handling boundary. This creates a privacy and unauthorized-processing risk because users may trigger collection, summarization, and onward document generation without understanding what data will be accessed or exposed.

Missing User Warnings

Medium
Confidence
96% confidence
Finding
The workflow includes creating Feishu documents, writing structured content, and modifying permissions, but it does not require explicit user confirmation before these side effects occur. That is dangerous because the skill can create new artifacts containing sensitive requirement data and grant access to other identities, leading to unintended disclosure or unauthorized collaboration exposure.

VirusTotal

66/66 vendors flagged this skill as clean.

View on VirusTotal