ClawHub
Back to skill

Security audit

Telegram Topic Message Sender

Security checks for vulnerabilities and agentic risk

Overview

This skill is a small, disclosed wrapper for sending user-provided text through OpenClaw messaging, with flexible Telegram target settings that users should verify before use.

Before installing, confirm that the configured OpenClaw channel auth is appropriate and check the `--channel`, `--chat-id`, and `--topic-id` values before running the script, since it can send messages to whichever destination those values select.

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
  • MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
  • 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
Findings (1)

Tp4

High
Category
MCP Tool Poisoning
Confidence
93% confidence
Finding
The skill is described as sending messages to a fixed Telegram topic, but the documented behavior allows runtime override of channel, chat ID, and topic ID. This expands the action from a narrowly scoped notification helper into a generic outbound messaging primitive, which can be abused to send messages to unintended destinations or even non-Telegram channels if the underlying CLI supports them.

Static analysis

No suspicious patterns detected.