ClawHub
Back to skill

Security audit

greetr

Security checks for vulnerabilities and agentic risk

Overview

This is a simple greeting skill with no code execution, persistence, credential access, or data movement; its only notable issue is a broad greeting trigger.

This skill is safe to install from a security standpoint based on the inspected artifact. Be aware that it may trigger on many casual greeting phrases because its activation wording is broad; tightening the trigger list would improve predictability.

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
97% confidence
Finding
The manifest says the skill should activate for listed greetings "or any greeting phrase," which makes the trigger boundary unclear and broad enough to overlap with common everyday speech. Because it does not define constraints or exclusions, the skill may invoke unexpectedly on many casual messages.

Vague Triggers

Medium
Confidence
93% confidence
Finding
The activation section includes common conversational phrases like "hi," "hey," and "what's up," plus "etc.," which leaves the full trigger set unspecified. This ambiguity increases the chance of unintended activation during ordinary conversation because no negative examples or context restrictions are provided.

Static analysis

No suspicious patterns detected.