ClawHub
Back to skill

Security audit

Supermemory

Security checks across malware telemetry and agentic risk

Overview

This skill is a disclosed Supermemory connector that can read, write, and delete Supermemory data through the OOMOL oo CLI, with user confirmation required for state-changing actions.

Install this only if you want the agent to use your connected Supermemory account. Review write or delete payloads carefully before approving them, because the skill can add memories, update memories, and permanently delete documents through Supermemory.

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 (1)

Vague Triggers

Medium
Confidence
93% confidence
Finding
The description says to use this skill for "ANY Supermemory request" and "instead of calling the API directly," which is an overly broad trigger that can cause the agent to invoke the skill in many contexts without enough task-specific validation. Because this skill supports read, write, and destructive operations, broad auto-selection increases the chance of unintended data access, modification, or deletion if the agent routes loosely related requests here.

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.