ClawHub

Feishu File Delivery

Security checks across malware telemetry and agentic risk

Overview

This skill openly helps send generated local files to Feishu chats, with the main risk being accidental attachment of the wrong file.

Install this only if you want generated files sent to Feishu as attachments. Before sending a final reply, verify every absolute path points to a file intended for that chat, and avoid listing secrets, unrelated documents, or sensitive local paths.

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 (3)

Missing User Warnings

Medium
Confidence
93% confidence
Finding
The README explicitly promotes automatically uploading local files into Feishu chats, but it does not warn users that absolute paths may reference sensitive local data and that including those paths in a reply causes real exfiltration to an external chat platform. In an agent setting, this increases the chance of accidental disclosure of confidential documents, exports, or files outside the intended task scope.

Missing User Warnings

Medium
Confidence
90% confidence
Finding
The skill explicitly instructs the agent to place absolute local file paths in the final Feishu reply so an outbound adapter will automatically upload those files as attachments. This creates an implicit data-exfiltration path without requiring explicit user confirmation at send time, and it also exposes internal filesystem paths in message text, which can leak sensitive environment details or cause unintended files to be transmitted if path handling is loose.

Missing User Warnings

Medium
Confidence
90% confidence
Finding
The skill explicitly describes an automatic upload to Feishu once a file path is produced, but it does not require explicit user confirmation or a clear warning that local files will be transmitted to an external service. This creates a real data-exfiltration risk because sensitive locally generated documents could be sent to a chat destination unintentionally, especially if the path is wrong, attacker-influenced, or the user does not realize delivery is automatic.

VirusTotal

66/66 vendors flagged this skill as clean.

View on VirusTotal