ClawHub
Back to skill

Security audit

Morty's Mind Blowers

Security checks across malware telemetry and agentic risk

Overview

This is a storytelling skill that openly reads memory files or logs to retell selected memories, with no code execution or hidden installation behavior found.

Install this only if you are comfortable with an agent reading memory files, transcripts, or logs to produce playful recaps. Avoid using it on stores that may contain secrets or highly sensitive personal information, and ask for a normal memory summary when you do not want the stylized mode.

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 trigger list is unusually broad and overlaps with generic memory-related requests such as 'random memory' and 'tell me a weird thing from memory.' That can cause the skill to activate when a user merely wants ordinary memory retrieval or summarization, leading to unintended access patterns, stylistic transformation of recalled content, and a higher chance of surfacing sensitive memories in the wrong context.

Vague Triggers

Medium
Confidence
81% confidence
Finding
The activation guidance says to use this skill for odd or revealing memory recaps 'instead of a plain summary,' but it does not clearly separate this from normal summarization or memory-browsing behavior. In a memory-accessing skill, that ambiguity increases the risk of inappropriate invocation and unnecessary transformation or exposure of archived content, especially when the skill is encouraged to 'rummage through memory' for something interesting.

VirusTotal

66/66 vendors flagged this skill as clean.

View on VirusTotal