ClawHub
Back to skill

Security audit

Telegram Bot Builder

Security checks for vulnerabilities and agentic risk

Overview

This skill is a straightforward Telegram Bot API helper; its network access and bot-token use are expected, but users should be careful with what they send and with the sample echo bot code.

Install only if you intend to let the agent operate a Telegram bot with the supplied bot token. Confirm chat IDs, user IDs, files, locations, and moderation actions before running commands, avoid sending secrets or unnecessary personal data through Telegram, and harden the echo-bot sample before using it in production.

A.I.G

Vulnerability Patterns
  • Insecure Skill Coding PracticesFinds exploitable flaws such as hardcoded secrets or command injection
  • 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
Findings (1)

T09 · Insecure Skill Coding Practices

Warning
Location
SKILL.md:296
Finding

Unsafe interpolation of attacker-controlled Telegram messages into JSON

Content
View full analysis
Remediation
View remediation

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 (49)

External Transmission

Medium
Category
Data Exfiltration
Confidence
50% confidence
Finding

Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.

Content

Scanner excerpt · SKILL.md (reported line 26)May include surrounding context.

All requests go to:

text
https://api.telegram.org/bot$TELEGRAM_BOT_TOKEN/METHOD_NAME

Usage

External Transmission

Medium
Category
Data Exfiltration
Confidence
50% confidence
Finding

Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.

Content

Scanner excerpt · SKILL.md (reported line 35)May include surrounding context.

All requests go to:

text
https://api.telegram.org/bot$TELEGRAM_BOT_TOKEN/METHOD_NAME

Usage

External Transmission

Medium
Category
Data Exfiltration
Confidence
50% confidence
Finding

Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.

Content

Scanner excerpt · SKILL.md (reported line 40)May include surrounding context.

All requests go to:

text
https://api.telegram.org/bot$TELEGRAM_BOT_TOKEN/METHOD_NAME

Usage

External Transmission

Medium
Category
Data Exfiltration
Confidence
50% confidence
Finding

Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.

Content

Scanner excerpt · SKILL.md (reported line 45)May include surrounding context.

All requests go to:

text
https://api.telegram.org/bot$TELEGRAM_BOT_TOKEN/METHOD_NAME

Usage

External Transmission

Medium
Category
Data Exfiltration
Confidence
50% confidence
Finding

Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.

Content

Scanner excerpt · SKILL.md (reported line 145)May include surrounding context.

All requests go to:

text
https://api.telegram.org/bot$TELEGRAM_BOT_TOKEN/METHOD_NAME

Usage

External Transmission

Medium
Category
Data Exfiltration
Confidence
50% confidence
Finding

Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.

Content

Scanner excerpt · SKILL.md (reported line 150)May include surrounding context.

All requests go to:

text
https://api.telegram.org/bot$TELEGRAM_BOT_TOKEN/METHOD_NAME

Usage

External Transmission

Medium
Category
Data Exfiltration
Confidence
50% confidence
Finding

Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.

Content

Scanner excerpt · SKILL.md (reported line 155)May include surrounding context.

All requests go to:

text
https://api.telegram.org/bot$TELEGRAM_BOT_TOKEN/METHOD_NAME

Usage

External Transmission

Medium
Category
Data Exfiltration
Confidence
50% confidence
Finding

Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.

Content

Scanner excerpt · SKILL.md (reported line 172)May include surrounding context.

All requests go to:

text
https://api.telegram.org/bot$TELEGRAM_BOT_TOKEN/METHOD_NAME

Usage

External Transmission

Medium
Category
Data Exfiltration
Confidence
50% confidence
Finding

Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.

Content

Scanner excerpt · SKILL.md (reported line 184)May include surrounding context.

All requests go to:

text
https://api.telegram.org/bot$TELEGRAM_BOT_TOKEN/METHOD_NAME

Usage

External Transmission

Medium
Category
Data Exfiltration
Confidence
50% confidence
Finding

Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.

Content

Scanner excerpt · SKILL.md (reported line 189)May include surrounding context.

All requests go to:

text
https://api.telegram.org/bot$TELEGRAM_BOT_TOKEN/METHOD_NAME

Usage

External Transmission

Medium
Category
Data Exfiltration
Confidence
50% confidence
Finding

Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.

Content

Scanner excerpt · SKILL.md (reported line 194)May include surrounding context.

All requests go to:

text
https://api.telegram.org/bot$TELEGRAM_BOT_TOKEN/METHOD_NAME

Usage

External Transmission

Medium
Category
Data Exfiltration
Confidence
50% confidence
Finding

Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.

Content

Scanner excerpt · SKILL.md (reported line 209)May include surrounding context.

All requests go to:

text
https://api.telegram.org/bot$TELEGRAM_BOT_TOKEN/METHOD_NAME

Usage

External Transmission

Medium
Category
Data Exfiltration
Confidence
50% confidence
Finding

Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.

Content

Scanner excerpt · SKILL.md (reported line 222)May include surrounding context.

All requests go to:

text
https://api.telegram.org/bot$TELEGRAM_BOT_TOKEN/METHOD_NAME

Usage

External Transmission

Medium
Category
Data Exfiltration
Confidence
50% confidence
Finding

Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.

Content

Scanner excerpt · SKILL.md (reported line 243)May include surrounding context.

All requests go to:

text
https://api.telegram.org/bot$TELEGRAM_BOT_TOKEN/METHOD_NAME

Usage

External Transmission

Medium
Category
Data Exfiltration
Confidence
50% confidence
Finding

Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.

Content

Scanner excerpt · SKILL.md (reported line 266)May include surrounding context.

All requests go to:

text
https://api.telegram.org/bot$TELEGRAM_BOT_TOKEN/METHOD_NAME

Usage

External Transmission

Medium
Category
Data Exfiltration
Confidence
50% confidence
Finding

Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.

Content

Scanner excerpt · SKILL.md (reported line 303)May include surrounding context.

All requests go to:

text
https://api.telegram.org/bot$TELEGRAM_BOT_TOKEN/METHOD_NAME

Usage

External Transmission

Medium
Category
Data Exfiltration
Confidence
50% confidence
Finding

Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.

Content

Scanner excerpt · SKILL.md (reported line 325)May include surrounding context.

All requests go to:

text
https://api.telegram.org/bot$TELEGRAM_BOT_TOKEN/METHOD_NAME

Usage

External Transmission

Medium
Category
Data Exfiltration
Confidence
60% confidence
Finding

Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.

Content

Scanner excerpt · SKILL.md (reported line 45)May include surrounding context.

Set bot commands

bash
curl -s -X POST "https://api.telegram.org/bot$TELEGRAM_BOT_TOKEN/setMyCommands" \
  -H "Content-Type: application/json" \
  -d '{
    "commands": [

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
94% confidence
Finding

The skill encourages sending messages, files, photos, and precise location data to Telegram without any explicit privacy or third-party data-transfer warning. Users may unknowingly transmit sensitive content to an external service, which is a genuine security/privacy risk in agent skills even though the destination is the intended Telegram API.

Content

No source excerpt is available for this finding.

External Transmission

Medium
Category
Data Exfiltration
Confidence
87% confidence
Finding

This duplicate finding corresponds to the sendMessage endpoint used to transmit user-chosen text to Telegram without warning about third-party disclosure. In this skill context, that omission is a legitimate privacy-risk issue.

Content

Scanner excerpt · SKILL.md (reported line 60)May include surrounding context.

Send text message

bash
curl -s -X POST "https://api.telegram.org/bot$TELEGRAM_BOT_TOKEN/sendMessage" \
  -H "Content-Type: application/json" \
  -d '{
    "chat_id": "CHAT_ID",

External Transmission

Medium
Category
Data Exfiltration
Confidence
87% confidence
Finding

This duplicate finding corresponds to the sendMessage endpoint used to transmit user-chosen text to Telegram without warning about third-party disclosure. In this skill context, that omission is a legitimate privacy-risk issue.

Content

Scanner excerpt · SKILL.md (reported line 60)May include surrounding context.

Send text message

bash
curl -s -X POST "https://api.telegram.org/bot$TELEGRAM_BOT_TOKEN/sendMessage" \
  -H "Content-Type: application/json" \
  -d '{
    "chat_id": "CHAT_ID",

External Transmission

Medium
Category
Data Exfiltration
Confidence
85% confidence
Finding

This duplicate finding covers the inline-keyboard sendMessage endpoint, which can transmit content and interactive metadata externally without warning. That omission creates a real disclosure/phishing-surface concern.

Content

Scanner excerpt · SKILL.md (reported line 71)May include surrounding context.

Send message with inline keyboard

bash
curl -s -X POST "https://api.telegram.org/bot$TELEGRAM_BOT_TOKEN/sendMessage" \
  -H "Content-Type: application/json" \
  -d '{
    "chat_id": "CHAT_ID",

External Transmission

Medium
Category
Data Exfiltration
Confidence
85% confidence
Finding

This duplicate finding covers the inline-keyboard sendMessage endpoint, which can transmit content and interactive metadata externally without warning. That omission creates a real disclosure/phishing-surface concern.

Content

Scanner excerpt · SKILL.md (reported line 71)May include surrounding context.

Send message with inline keyboard

bash
curl -s -X POST "https://api.telegram.org/bot$TELEGRAM_BOT_TOKEN/sendMessage" \
  -H "Content-Type: application/json" \
  -d '{
    "chat_id": "CHAT_ID",

External Transmission

Medium
Category
Data Exfiltration
Confidence
84% confidence
Finding

This duplicate finding covers the reply-keyboard sendMessage endpoint, including keyboard actions that may request location. Lack of privacy guidance makes the example risky in agent use.

Content

Scanner excerpt · SKILL.md (reported line 87)May include surrounding context.

Send message with reply keyboard

bash
curl -s -X POST "https://api.telegram.org/bot$TELEGRAM_BOT_TOKEN/sendMessage" \
  -H "Content-Type: application/json" \
  -d '{
    "chat_id": "CHAT_ID",

External Transmission

Medium
Category
Data Exfiltration
Confidence
84% confidence
Finding

This duplicate finding covers the reply-keyboard sendMessage endpoint, including keyboard actions that may request location. Lack of privacy guidance makes the example risky in agent use.

Content

Scanner excerpt · SKILL.md (reported line 87)May include surrounding context.

Send message with reply keyboard

bash
curl -s -X POST "https://api.telegram.org/bot$TELEGRAM_BOT_TOKEN/sendMessage" \
  -H "Content-Type: application/json" \
  -d '{
    "chat_id": "CHAT_ID",