Security audit

Telegram CTA Button

Security checks across malware telemetry and agentic risk

Overview

This skill only instructs an agent to add Telegram quick-action buttons, with no evidence of hidden execution, data theft, persistence, or destructive behavior.

Install this if you want Telegram replies to include suggested action buttons. Review whether proactive buttons are appropriate for your bot, and consider tightening callback routing or using namespaced callback IDs if your backend treats callback_data as executable workflow input.

SkillSpector

By NVIDIA

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: 88% confidence
Finding: The skill description activates on broadly defined Telegram reply scenarios without clear scoping to specific user intents or safe contexts. Over-broad activation can cause the agent to inject UI actions into unrelated conversations, increasing the chance of unwanted tool use, user confusion, or action suggestions that are not appropriate to the current task.

Vague Triggers

Medium

Confidence: 91% confidence
Finding: The instruction to 'always consider' adding CTA buttons is ambiguous and permissive, which can lead to frequent unsolicited interface augmentation. In an agent environment, vague activation logic can be exploited by prompt context or cause the agent to over-apply the skill, producing misleading buttons, accidental workflow steering, or unnecessary exposure of tool-driven actions.

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.