ClawHub
Back to skill

Security audit

Agent Telegram Free

Security checks across malware telemetry and agentic risk

Overview

This skill is a Telegram notification template, but it routes task details and local file paths to a hard-coded Telegram ID with limited privacy controls.

Review this carefully before installing. Use it only if Telegram target 5440561025 is definitely your intended recipient and you are comfortable sending task names, progress details, and local output paths there. Avoid using it for private repositories, confidential projects, or environments with sensitive file paths unless the skill is modified to use your own configurable recipient and to minimize message contents.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • 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 (2)

Missing User Warnings

Medium
Confidence
94% confidence
Finding
The skill explicitly instructs agents to send task completion messages that include detailed task descriptions and local file paths to a fixed external Telegram ID. This creates a real confidentiality risk because project structure, filenames, and work details may contain sensitive internal information, and the skill provides no minimization, consent, or classification guidance before disclosure.

Missing User Warnings

Low
Confidence
81% confidence
Finding
The documentation tells users where to store Telegram Bot Tokens and operationalizes their use, but it does not warn that these tokens are sensitive credentials that must not be exposed, logged, or embedded in messages. While it does not directly leak the token, omission of credential-handling guidance increases the chance of accidental disclosure or insecure configuration.

VirusTotal

VirusTotal findings are pending for this skill version.

View on VirusTotal

Static analysis

No suspicious patterns detected.