Feishu DM Sender

• Outcome: Pass
• Latest audit: May 29, 2026 at 8:23 PM UTC
• Version:
  1.0.0

Overview

This skill does what it claims: it sends Feishu/Lark messages using the user's configured OpenClaw Feishu credentials.

Install only if you want your agent to send Feishu/Lark DMs or group messages. Protect openclaw.json because it contains app credentials, keep Feishu app permissions narrow, and require user confirmation or recipient limits before sending sensitive task outputs, logs, secrets, or private data.

SkillSpector

By NVIDIA

Vulnerability Patterns

• Prompt Injection: Instruction Override, Hidden Instructions, Exfiltration Commands
• Trigger Abuse: Overly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
• MCP Least Privilege: Underdeclared Capability, Wildcard Permission, Missing Permission Declaration
• Data Exfiltration: External Transmission, Env Variable Harvesting, File System Enumeration
• Privilege Escalation: Excessive Permissions, Sudo/Root Execution, Credential Access

Findings (3)

Lp3

Medium

• Category: MCP Least Privilege
• Confidence: 89% confidence
• Finding: The skill documentation describes capabilities to read local configuration (`~/.openclaw/openclaw.json`) and send network requests to Feishu, but it does not declare corresponding permissions. Undeclared file-read and network capabilities reduce transparency and can cause an agent or reviewer to underestimate the skill's access to credentials and its ability to transmit data off-host.

Vague Triggers

Medium

• Confidence: 78% confidence
• Finding: The invocation guidance is broad: 'agent needs to notify someone, send task results, or communicate with team members' can match many normal workflows and may cause the skill to be selected automatically in situations involving sensitive data. Because this skill can message arbitrary users or chats, broad triggering increases the chance of unintended disclosure through overuse or misuse.

Exfiltration Commands

High

• Category: Prompt Injection

Content

---
name: feishu-send-message
description: |
  Proactively send messages to Feishu (Lark) users or group chats from your OpenClaw agent.
  Supports name-based lookup from DM contacts config, open_id, and chat_id.
  Zero dependencies — uses only Python 3 stdlib. Reads credentials from openclaw.json automatically.
  Use when: agent needs to notify someone, send task results, or communicate with team members on Feishu.

• Confidence: 92% confidence
• Finding: send messages to

VirusTotal

64/64 vendors flagged this skill as clean.