Telegram cli

• Outcome: Review
• Latest audit: May 29, 2026 at 9:27 PM UTC
• Version:
  1.0.5

Overview

This Telegram skill is coherent, but it gives an agent broad persistent access to private Telegram account actions without enough consent and privacy guardrails.

Install only if you are comfortable giving a CLI persistent access to your Telegram account. Use a dedicated account if possible, review the external npm package, log out when finished, and require explicit approval before reading broad inbox data, searching all chats, sending or deleting messages, forwarding content, downloading media, or changing groups and contacts.

SkillSpector

By NVIDIA

Vulnerability Patterns

• Trigger Abuse: Overly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
• Prompt Injection: Instruction Override, Hidden Instructions, Exfiltration Commands
• Data Exfiltration: External Transmission, Env Variable Harvesting, File System Enumeration
• Privilege Escalation: Excessive Permissions, Sudo/Root Execution, Credential Access
• Supply Chain: Unpinned Dependencies, External Script Fetching, Obfuscated Code

Findings (2)

Vague Triggers

Medium

• Confidence: 92% confidence
• Finding: The skill description is broad enough to trigger for many ordinary Telegram-related requests, which can cause an agent to select a high-privilege messaging tool when a lower-risk response would suffice. In context, this increases the chance of unnecessary access to account data, private conversations, and message-sending capabilities.

Missing User Warnings

Medium

• Confidence: 95% confidence
• Finding: The skill advertises inbox listing, chat search, global search, and chat inspection without warning that these operations expose sensitive private communications, contact graphs, and metadata. Because this is a Telegram account tool, normal use could reveal highly sensitive user content unless the skill clearly limits access to user-specified chats and queries.

VirusTotal

66/66 vendors flagged this skill as clean.