ClawHub
Back to skill

Security audit

Telegram Alert Tool Free

Security checks across malware telemetry and agentic risk

Overview

This skill is mostly a Telegram trading-alert guide, but its broad activation wording and inconsistent free-tier limits could cause unintended outbound messaging.

Review this before installing if you only want a narrowly scoped Telegram trading-alert skill. Keep the bot token private, use it only for a single intended chat, and avoid letting an agent use this skill for generic messaging, email/SMS, bulk outreach, or scheduled broadcasts unless the publisher clarifies and enforces those capabilities.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Findings (4)

Description-Behavior Mismatch

Medium
Confidence
92% confidence
Finding
The free-edition capability table explicitly says timed push notifications are not supported, yet the usage section documents a working `schedule` command for daily broadcasts. This inconsistency can mislead an agent into invoking unsupported behavior, expanding the skill's effective permission/scope beyond what the manifest claims and weakening policy or billing controls tied to edition limits.

Description-Behavior Mismatch

Medium
Confidence
89% confidence
Finding
The manifest states the free version is limited to a single Telegram group, but the generic operation descriptions (`create/query/export`, `modify/reset/import`) do not define or enforce that restriction. In an agent context, ambiguous capability descriptions can enable over-broad use, including configuring multiple destinations or importing broader configs than intended.

Vague Triggers

Medium
Confidence
90% confidence
Finding
The skill advertises extremely broad activation phrases such as general message sending, notification pushing, email/SMS, and communication integration, despite being a Telegram alert tool. Over-broad triggers can cause an agent to select this skill for unrelated messaging tasks, increasing the chance of unintended external communications or misuse for spam-like actions.

Vague Triggers

Medium
Confidence
94% confidence
Finding
The capability coverage section lists an excessively broad set of keywords, including fragmented and generic phrases like 'Use when', '需要消息发送', and '工作流场景', which can bias agent selection toward this skill across many unrelated tasks. In a tool with `write` and `exec` access plus outbound messaging, over-selection materially raises the risk of unauthorized or accidental message delivery.

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.