Back to skill

Security audit

tlgr

Security checks for vulnerabilities and agentic risk

Overview

The skill is a disclosed Telegram CLI integration with powerful account access, but its sensitive behavior is purpose-aligned and includes user-control guidance.

Install only if you are comfortable giving the CLI access to your personal Telegram account. Use command restrictions for read-only or narrow tasks, avoid pasting passwords into chat, and require explicit confirmation before sending to new contacts, deleting, blocking, leaving chats, or changing account settings.

Vulnerability Patterns
  • Skill Instruction HijackingAlters the agent's session goals or safety constraints when the skill loads
  • Agent Memory PoisoningWrites attacker-controlled rules into memory that affect later sessions
  • Remote Payload Retrieval and ExecutionFetches external code whose behavior can change after review
  • Embedded Malicious CodeShips malicious scripts inside the skill and executes them locally
  • Unauthorized Access and Privilege EscalationObtains permissions beyond the task's legitimate needs
Vulnerability Patterns
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
  • 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)

Autonomous Decision Making

Medium
Category
Excessive Agency
Confidence
80% confidence
Finding

Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.

Content

Scanner excerpt · SKILL.md (reported line 97)May include surrounding context.

md
Ask the user for the code Telegram sends them. Exit 4 with
`AUTH_PASSWORD_REQUIRED` means two-step verification is on: rerun
`verify-code` with `--password-env TLGR_2FA_PASSWORD` after the user sets
that variable. Never ask the user to paste a password into the chat.

## Reacting to events

Static analysis

No suspicious patterns detected.