ClawHub
Back to skill

Security audit

Telegram Alerts

Security checks for vulnerabilities and agentic risk

Overview

This is a simple Telegram notification skill whose behavior matches its stated trading-alert purpose, but users should treat trade and portfolio messages and the bot token as sensitive.

Use this only for information you are comfortable sending through Telegram. Keep TELEGRAM_BOT_TOKEN private, do not commit .env files, restrict the bot/chat to intended recipients, and be cautious with portfolio summaries or scheduled reports that reveal holdings or trading behavior.

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
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • YARA SignaturesMalware Match, Webshell Match, Cryptominer Match
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (4)

YARA rule 'ransomware_behavior': Ransomware-like patterns (mass encryption, ransom notes) [malware]

Critical
Category
YARA Match
Confidence
80% confidence
Finding

YARA rule matched a known malware signature (reverse shell, backdoor, ransomware, C2 framework, or info stealer).

Content

Scanner excerpt · SKILL.md (reported line 22)May include surrounding context.

io update.

Alert Types

  • Trade alerts: entry/exit with P&L, entry price, stop, target
  • Price alerts: trigger when asset crosses threshold
  • Portfolio summaries: NAV, daily P&L, positions
  • Stop-loss warnings: drawdown approaching limit
  • Win/loss streaks: celebration + tilt prevention
  • Scheduled reports: daily 18:00, weekly Monday

Usage

text
Use telegram-alerts to send a trade entry notification for BTC LONG at $68,000

Use telegram-alerts to send my daily portfolio summary

Use telegram-alerts to alert me when SOL breaks $90

Format Example

text
🟢 TRADE OPENED
Asset: BTC/USDT | LONG
Entry: $68,247 | Stop: $67,200 | Target: $70,000
Risk: $0.38 (0.05% NAV) | R:R = 1:2.6

Setup

Requires TELEGRAM_BOT_TOKEN and TELEGRAM_CHAT_ID in your .env file.

Credential Access

High
Category
Privilege Escalation
Confidence
60% confidence
Finding

Code accesses credential files (SSH keys, AWS credentials, etc.). This could indicate credential theft attempts.

Content

Scanner excerpt · SKILL.md (reported line 38)May include surrounding context.

text

## Setup
Requires TELEGRAM_BOT_TOKEN and TELEGRAM_CHAT_ID in your .env file.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
91% confidence
Finding

The skill explicitly sends trading and portfolio information to Telegram, an external third-party messaging service, but the description does not warn users that potentially sensitive financial data will leave the local environment. This creates a real privacy and operational-security risk because users may disclose holdings, positions, and trading behavior without informed consent.

Content

No source excerpt is available for this finding.

Missing User Warnings

Low
Category
Not specified by scanner
Confidence
88% confidence
Finding

The setup section requires TELEGRAM_BOT_TOKEN and TELEGRAM_CHAT_ID but does not warn that the bot token is a sensitive secret that can enable unauthorized message sending if exposed. While the document does not directly leak credentials, weak guidance around secret handling can lead to accidental disclosure or unsafe storage practices.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.