Back to plugin

Security audit

openclaw-lark-2

Security checks for vulnerabilities and agentic risk

Overview

The plugin’s account access, messaging, document tools, and formatting guidance fit its stated Feishu/Lark purpose.

This is a third-party integration with shell access and potentially broad Feishu permissions. Grant only needed permissions, restrict who can use the bot, verify account profiles, and configure separate sessions where accounts require isolation. Tool activity appears in chat by default; use /verbose off when appropriate.

Vulnerability Patterns
  • System Prompt LeakageDirect Leakage, Indirect Extraction, Tool-Based Exfiltration
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Findings (2)

Direct Prompt Extraction

High
Category
System Prompt Leakage
Confidence
85% confidence
Finding

Skill contains instructions that could directly expose system prompts, internal rules, or hidden instructions to users or external parties.

Content

Scanner excerpt · skills/feishu-channel-rules/SKILL.md (reported line 12)May include surrounding context.

md
(3) 用户提到"飞书格式"、"卡片语法"、"markdown"
---

# Lark Output Rules

> 常用的输出风格规则由插件在**每一轮的 Message Context** 中自动注入(`inboundFormattingHints`),无需本 skill 常驻;本 skill 提供**详细语法参考**,按需查阅。

The activation list includes the generic term "markdown" without an explicit Lark/Feishu restriction.

Low
Category
Trigger Abuse
Confidence
92% confidence
Finding

Although the skill's description focuses on Lark/Feishu formatting, this activation condition says to use it when the user mentions "markdown". That term also appears in unrelated documentation and formatting requests, so the explicit trigger can cause unintended invocations outside the skill's domain.

Content

No source excerpt is available for this finding.

Endor dependency reachability

Checked Nov 16, 2026 · 9:07 AM UTC

No reachable vulnerabilities reported

Endor dependency scan completed.