ClawHub

Nova Letters

Security checks across malware telemetry and agentic risk

Overview

This is a simple local journaling skill, but its read command can escape the intended letters folder and expose other Markdown files.

Install only with caution. The journaling behavior is understandable, but the read command should be fixed to accept only validated dates and to ensure resolved paths stay inside `~/.openclaw/workspace/letters/`. Avoid storing secrets or highly sensitive personal/business details unless you are comfortable with plaintext local files.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Rogue AgentSelf-Modification, Session Persistence
  • 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)

Missing User Warnings

Medium
Confidence
93% confidence
Finding
The skill explicitly stores reflective letters in a persistent directory under the user's home folder, and the content is likely to contain sensitive personal thoughts, project details, or other private context. Failing to clearly warn users about persistent on-disk storage can lead to unintentional retention and later exposure through backups, shared machines, or other local access.

Session Persistence

Medium
Category
Rogue Agent
Content
---
name: nova-letters
description: Write reflective letters to your future self. Capture what matters across sessions.
---

# nova-letters
Confidence
90% confidence
Finding
Write reflective letters to your future self. Capture what matters across sessions. --- # nova-letters Write letters to your future self. For every session that wakes up not knowing what happened ye

VirusTotal

66/66 vendors flagged this skill as clean.

View on VirusTotal