ClawHub
Back to skill

Security audit

Telegram Routing

Security checks for vulnerabilities and agentic risk

Overview

This skill clearly manages OpenClaw Telegram routing by editing a local OpenClaw config and restarting the gateway, with no evidence of hidden code or unrelated data access.

Before using model, fallback, or restore commands, be aware they can persistently change how Telegram messages are routed and may switch between CLI and API providers. Back up ~/.openclaw/openclaw.json first and confirm the selected model/provider is intended.

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)

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The skill explicitly instructs changing a user-local configuration file and restarting a gateway service, but provides no warning, confirmation step, backup guidance, or rollback protections. In an agent-driven environment, this can cause unintended service disruption, misrouting of messages, or persistence of incorrect settings if the command is followed automatically or without informed user consent.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.