ClawHub
Back to skill

Security audit

Telegram Bot

Security checks across malware telemetry and agentic risk

Overview

The skill is a coherent Telegram Bot connector, but it under-labels several state-changing moderation actions as safe read-like actions.

Review before installing if this bot manages real groups, channels, business messages, or webhooks. Require explicit user confirmation for every Telegram action that posts, deletes, moderates users, changes permissions, changes admin status, pins or unpins messages, marks business messages read, or changes webhook/invite settings, even when the skill does not label the action as write or destructive.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • 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)

Vague Triggers

High
Confidence
93% confidence
Finding
The manifest description says to use this skill for ANY Telegram Bot request and instead of calling the API directly, which is an overly broad trigger that can cause the agent to invoke this skill in situations where narrower, safer logic or direct user confirmation would be more appropriate. Because this skill exposes many write and destructive actions, broad auto-selection increases the chance of unintended state-changing operations or over-privileged use when a task merely mentions Telegram.

VirusTotal

VirusTotal findings are pending for this skill version.

View on VirusTotal

Static analysis

No suspicious patterns detected.