ClawHub
Back to skill

Security audit

content-memory

Security checks across malware telemetry and agentic risk

Overview

The skill clearly provides external memory, but it tells agents to automatically save interaction summaries to a third-party service without clear user approval, limits, or deletion guidance.

Install only if you are comfortable with content ideas, drafts, and interaction summaries being sent to BlueColumn for persistent memory. Avoid using it for confidential, personal, regulated, or proprietary material unless you have clear consent, retention, and deletion practices in place.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
Findings (2)

Missing User Warnings

Medium
Confidence
95% confidence
Finding
The skill instructs agents to send recalled context and post-interaction summaries to an external persistent memory service, but it does not clearly warn users that their content may be transmitted to and retained by a third party. This creates a privacy and consent gap: users may disclose sensitive drafts, ideas, or interaction details without understanding that they are being stored outside the primary system.

Ssd 3

Medium
Confidence
97% confidence
Finding
The workflow says to store a summary after every interaction, which encourages routine persistence of conversation-derived data in natural language form. This can easily capture sensitive prompts, proprietary content, personal data, or confidential drafts, increasing the risk of data leakage, over-retention, and unintended reuse if the external memory store is later queried or exposed.

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.