ClawHub
Back to skill

Security audit

Feishu App Bot

Security checks for vulnerabilities and agentic risk

Overview

This skill is a disclosed Feishu App Bot connector with broad account actions, and its main caution is an unverified remote CLI installer in the setup instructions.

Install only if you intend to let the agent operate your connected Feishu App Bot account. Review every write or destructive action before approval, and prefer verifying or manually installing the oo CLI instead of blindly running the pipe-to-shell setup commands.

A.I.G

Vulnerability Patterns
  • Skill Instruction HijackingAlters the agent's session goals or safety constraints when the skill loads
  • Agent Memory PoisoningWrites attacker-controlled rules into memory that affect later sessions
  • Remote Payload Retrieval and ExecutionFetches external code whose behavior can change after review
  • Embedded Malicious CodeShips malicious scripts inside the skill and executes them locally
  • Unauthorized Access and Privilege EscalationObtains permissions beyond the task's legitimate needs

SkillSpector

Vulnerability Patterns
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
  • 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)

External Script Fetching

High
Category
Supply Chain
Confidence
98% confidence
Finding

The first-time setup instructions recommend piping a remote script directly into a shell (curl ... | bash), which allows immediate execution of code fetched at runtime without integrity verification. If the install endpoint, transport, or distribution pipeline is compromised, users could execute arbitrary attacker-controlled code on their machine.

Content

Scanner excerpt · SKILL.md (reported line 386)May include surrounding context.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The skill description says to use this skill for ANY Feishu App Bot request instead of calling the API directly, which is an unusually broad routing instruction. In an agentic system, that can cause over-selection of a highly privileged skill for routine or ambiguous Feishu-related tasks, increasing the chance of unintended reads, writes, or destructive operations through the connected account.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.