ClawHub

Feishu Send Voice

Security checks across malware telemetry and agentic risk

Overview

This skill does what it claims: converts text to audio and sends it through Feishu, using local Feishu credentials that are disclosed in the docs.

Install only if you want agents to send Feishu voice messages using your configured Feishu app. Confirm the message text and recipient open_id before running it, and use least-privilege Feishu credentials because the script reads local credentials and transmits the generated audio to Feishu.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (1)

Lp3

Medium
Category
MCP Least Privilege
Confidence
93% confidence
Finding
The skill instructs the agent to invoke a shell script and read local configuration from ~/.openclaw/openclaw.json, but it does not declare corresponding permissions. This creates a trust and review gap: users or the platform may not realize the skill can execute shell commands and access local files containing Feishu credentials, increasing the risk of unintended secret exposure or command execution in agent contexts.

VirusTotal

66/66 vendors flagged this skill as clean.

View on VirusTotal