ClawHub
Back to skill

Security audit

greetr

Security checks across malware telemetry and agentic risk

Overview

This is a simple greeting skill whose only effect is to produce short time-aware greetings.

Install this if you want automatic friendly greetings. The only notable tradeoff is that its broad activation wording may make it respond to casual greeting-like phrases when you might have expected normal conversation or another skill.

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
90% confidence
Finding
The skill advertises activation on very common greeting phrases, which can cause it to trigger in many ordinary conversations without a clearly bounded invocation scope. While the behavior is low risk because it only produces a greeting, over-broad matching can still create unintended routing, interfere with other skills, or cause user input to be handled by the wrong capability.

Vague Triggers

Medium
Confidence
87% confidence
Finding
Using ambiguous examples such as 'what's up' and 'etc.' leaves the activation boundary underspecified, making the skill more likely to match casual speech that may not be intended as a greeting invocation. In this context the impact is limited because the skill's action is only to greet, but the ambiguity still weakens predictable and safe skill selection behavior.

VirusTotal

61/61 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.