ClawHub
Back to skill

Security audit

Prompt Log

Security checks across malware telemetry and agentic risk

Overview

This skill is a local transcript-export helper; its main risk is that exported AI session logs can contain sensitive information.

Install only if you intend to export local AI session history. Treat both source logs and generated transcripts as sensitive, avoid committing .prompt-log or transcript files to shared repositories, choose a protected output path when needed, and inspect any scripts/extract.sh implementation before running it.

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 (1)

Missing User Warnings

Medium
Confidence
95% confidence
Finding
The skill explicitly writes exported conversation transcripts to disk but does not warn that session logs and generated transcripts may contain sensitive prompts, secrets, tokens, file paths, or proprietary code. This omission can lead users to unintentionally persist confidential data in project directories or other locations where it may be exposed, committed, or shared.

VirusTotal

65/65 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.