ClawHub
Back to skill

Security audit

Feishu New Chat

Security checks for vulnerabilities and agentic risk

Overview

This skill posts user-requested Feishu topic messages and thread replies, with clear limits and no bundled executable code.

Install only if you want the agent to create Feishu topic-group posts as you. Be aware that when you ask it to carry prior context into a new topic, a short summary of that context may be posted into the selected Feishu group.

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
  • 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
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
Findings (1)

Exfiltration Commands

High
Category
Prompt Injection
Confidence
90% confidence
Finding

Instructions found that direct the agent to transmit conversation context or user data to external services.

Content

Scanner excerpt · SKILL.md (reported line 234)May include surrounding context.

md
- This skill only works as intended in a **Feishu topic-group**.
- This skill does **not** create Feishu groups.
- This skill should not silently send as the user unless the user explicitly asked.
- This skill is for **topic bootstrapping**: create the topic, optionally seed the first thread reply, then let later conversation continue inside that topic.
- If the user wants a normal group message instead of a topic, do not force this skill.

Static analysis

No suspicious patterns detected.