ClawHub
Back to skill

Security audit

Feishu Send File 1.2.1

Security checks across malware telemetry and agentic risk

Overview

This skill openly sends user-selected local files or images through Feishu/Lark, with credential-handling cautions but no hidden or unrelated behavior found.

Install only if you intend to send local files or images through a Feishu/Lark app. Verify the file path and recipient before running it, avoid sensitive or regulated files unless authorized, and prefer adapting the scripts to read app_secret from a protected environment variable or secret store instead of command-line arguments.

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 documentation tells operators to pass sensitive values such as app_secret and recipient identifiers directly on the command line for network transmission, but provides no explicit warning about credential exposure or privacy risks. Command-line secrets can leak through shell history, process listings, logs, or debugging output, and recipient IDs are potentially sensitive metadata.

Missing User Warnings

Medium
Confidence
84% confidence
Finding
This skill is explicitly designed to upload a local file to a remote Feishu/Lark API, which creates a real data-exfiltration risk if the caller supplies a sensitive path or if the skill is invoked without clear disclosure and consent. In an agent setting, the ability to transmit arbitrary local files off-host is materially dangerous because it crosses a trust boundary from local filesystem to external network service.

VirusTotal

61/61 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.