ClawHub
Back to skill

Security audit

多机器人去重消息

Security checks for vulnerabilities and agentic risk

Overview

This skill is a narrow Feishu multi-bot deduplication rule that stores minimal local state to avoid duplicate replies.

Install this only for Feishu/OpenClaw setups where the same user message can arrive through multiple bot channels. Be aware that it stores small local per-sender deduplication records and may intentionally skip near-duplicate replies for 30 seconds.

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 (2)

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
83% confidence
Finding

The natural-language description and instructions are entirely in Chinese and are framed as a mandatory behavior specification for the AI, but they do not indicate that language choice is optional or limited to a China/Chinese-language deployment. This can violate language/locale policy when used in broader environments because it implicitly forces a specific language context without user opt-in.

Content

No source excerpt is available for this finding.

Missing User Warnings

Low
Category
Not specified by scanner
Confidence
77% confidence
Finding

This markdown skill instructs the system to read and update dedup_state.json based on sender_id, reply time, and a message-content hash, but it does not warn users that conversation metadata will be persisted and used to suppress later replies. Because the behavior affects user data handling and can change whether the user receives a response, a brief disclosure is warranted in the skill description.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.