ClawHub
Back to skill

Security audit

Telegram CTA Button

Security checks for vulnerabilities and agentic risk

Overview

This skill only provides guidance for adding Telegram quick-action buttons and does not add hidden code, persistence, credential access, or destructive behavior.

Before installing, expect the agent to add Telegram CTA buttons more often during Telegram conversations. This is mainly a usability preference; review the button text and callback actions if you want tighter limits on when buttons appear.

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
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • 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 (2)

Vague Triggers

Medium
Confidence
92% confidence
Finding
The description says to use the skill 'when replying to users on Telegram,' which is a very broad activation condition and does not clearly distinguish when the skill should or should not be used. It also lacks negative examples or narrower trigger criteria, increasing the chance of unintended invocation across ordinary Telegram interactions.

Vague Triggers

Low
Confidence
84% confidence
Finding
The phrase 'always consider if providing quick-action buttons would improve efficiency' is open-ended and subjective, leaving unclear boundaries for use. Without explicit criteria for when buttons should not be added, this can lead to over-application of the skill in routine conversations.

Static analysis

No suspicious patterns detected.