ClawHub
Back to skill

Security audit

Telegram Login Helper

Security checks for vulnerabilities and agentic risk

Overview

The skill is coherent for Telegram personal-account login, but it encourages reuse and copying of authenticated TDLib session state for a named local account without clear consent, secrecy, or handling guardrails.

Review before installing. Only use this skill for Telegram accounts you own or are explicitly authorized to administer. Treat TDLib data directories and TELEGRAM_API_ID/TELEGRAM_API_HASH as secrets, avoid copying session state between machines unless the transfer and storage are protected, and remove or adapt the hardcoded steve paths/namespaces before use in any shared environment.

A.I.G

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

SkillSpector

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 (5)

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
92% confidence
Finding

The skill explicitly recommends copying an existing TDLib session/state directory between machines or namespaces to bypass re-authentication, but it does not warn that this state likely contains highly sensitive authentication material and account data. Mishandling or reusing these files can enable unauthorized account access, session hijacking, and unintended disclosure of private Telegram content, especially because the skill is specifically about personal-account access.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

This runbook provides operational steps for logging into and reusing a Telegram personal account, including copying TDLib state and using API credentials, but it omits any privacy, consent, or account-security warnings. In context, the file is explicitly about accessing a personal account and reading chats/history, so normalizing session reuse and state copying without guardrails increases the risk of unauthorized account access, message exposure, and credential mishandling.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
95% confidence
Finding

The operational instructions are presented in Chinese, but the file does not indicate that Chinese is required for a specific audience or provide an opt-in language choice. This can violate a language/locale policy when users or agents are expected to receive instructions in a selectable or default organizational language.

Content

No source excerpt is available for this finding.

Missing User Warnings

Low
Category
Not specified by scanner
Confidence
81% confidence
Finding

The skill instructs users to use TELEGRAM_API_ID and TELEGRAM_API_HASH for MTProto/code login without warning that these are sensitive credentials that should not be exposed in logs, scripts, or shared environments. In a login-helper context, users may paste or persist these secrets insecurely, which can lead to unauthorized API use or compromise of Telegram application credentials.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
84% confidence
Finding

The operational instructions are written in Chinese and direct another agent/operator through the procedure, but there is no indication that Chinese is optional or that this locale constraint is required for a region-specific purpose. Under SQP-3, forcing a specific language without user opt-in is a natural-language policy concern.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.