ClawHub
Back to skill

Security audit

remember-podcasts

Security checks across malware telemetry and agentic risk

Overview

This skill is a small podcast-note memory helper that sends user-provided notes and searches to a disclosed BlueColumn/Supabase API, with no hidden code or install-time behavior found.

Install only if you are comfortable sending podcast notes, timestamps, summaries, and searches to BlueColumn's hosted service. Avoid submitting confidential or regulated content unless your organization approves it, and treat the BlueColumn API key like a password.

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 users to send podcast notes, summaries, and search queries to a third-party remote endpoint without any explicit privacy or data-sharing warning. Because those notes may contain personal interests, work discussions, or sensitive business context, users may disclose data externally without informed consent.

Missing User Warnings

Medium
Confidence
93% confidence
Finding
The examples place a live API credential in an Authorization header using a shell variable but provide no warning about shell history, process listings, terminal logging, CI logs, or screen sharing exposing the token. This increases the chance of credential leakage, which could let an attacker access the user's BlueColumn account and any stored notes or search capabilities.

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.