ClawHub
Back to skill

Security audit

Telegram Voice Bot

Security checks across malware telemetry and agentic risk

Overview

The bot appears to do what it claims, but users should review it because it handles voice content and bot credentials while using ambiguous, unpinned dependencies and automatic transcript replies.

Install only in an isolated environment after reviewing and pinning dependencies, especially replacing or verifying the intended Whisper package. Use a dedicated Telegram bot token, keep it secret, disclose voice/transcript handling to chat participants, and avoid adding the bot to sensitive group chats unless automatic transcript replies are acceptable.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
Findings (8)

Missing User Warnings

Medium
Confidence
83% confidence
Finding
The README advertises voice recognition and speech synthesis but does not disclose that user audio may be transmitted to external services such as OpenAI Whisper and Microsoft Edge TTS. This omission can lead operators to deploy the bot without informing end users or assessing privacy, consent, and data-handling obligations for voice data.

Missing User Warnings

Low
Confidence
74% confidence
Finding
The README instructs users to set TELEGRAM_BOT_TOKEN but does not explicitly warn that the token is a sensitive secret that must not be committed, logged, or shared. This increases the chance of accidental credential exposure, which would allow attackers to control the bot and impersonate it.

Missing User Warnings

Medium
Confidence
93% confidence
Finding
The skill advertises voice recognition and speech synthesis but does not clearly warn users that voice content may be transmitted to external processing components or services, creating a privacy and consent gap. For a Telegram bot handling voice messages, users may reasonably assume messages stay within Telegram or the local bot unless explicitly told otherwise, so omission of this disclosure can expose sensitive spoken data without informed consent.

Ssd 3

Medium
Confidence
92% confidence
Finding
The bot automatically echoes the full transcribed contents of a user's voice message back into chat and optionally as synthesized speech. This increases exposure of potentially sensitive spoken content, especially in group chats, shared devices, or cases where speech recognition mis-transcribes private data into visible text/audio.

Unpinned Dependencies

Low
Category
Supply Chain
Content
requests
whisper
edge-tts
Confidence
95% confidence
Finding
requests

Unpinned Dependencies

Low
Category
Supply Chain
Content
requests
whisper
edge-tts
Confidence
87% confidence
Finding
whisper

Unpinned Dependencies

Low
Category
Supply Chain
Content
requests
whisper
edge-tts
Confidence
87% confidence
Finding
edge-tts

Known Vulnerable Dependency: requests — 10 advisory(ies): CVE-2014-1830 (Exposure of Sensitive Information to an Unauthorized Actor in Requests); CVE-2024-47081 (Requests vulnerable to .netrc credentials leak via malicious URLs); CVE-2024-35195 (Requests `Session` object does not verify requests after making first request wi) +7 more

High
Category
Supply Chain
Confidence
98% confidence
Finding
requests

VirusTotal

66/66 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.