Back to skill

Security audit

telegram-formatting

Security checks across malware telemetry and agentic risk

Overview

This skill only teaches Telegram message formatting and does not add hidden access, background execution, or credential handling.

Installers should know this skill may cause the agent to check OpenClaw settings/version and, when rich Telegram rendering is uncertain, send a small test message before using a formatting block. There is no evidence of credential access, data exfiltration, destructive behavior, or unrelated automation.

SkillSpector

By NVIDIA
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

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.