ClawHub
Back to skill

Security audit

Last.fm

Security checks across malware telemetry and agentic risk

Overview

This is a read-only Last.fm helper whose account-linked listening data access is disclosed and aligned with its purpose.

Install only if you are comfortable letting the agent query and display Last.fm data tied to the configured username. Use HTTPS for the documented API URLs where supported, keep the API key out of shared logs/screenshots, and rotate the key if it is exposed.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • 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
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
Findings (1)

Missing User Warnings

Medium
Confidence
95% confidence
Finding
The skill explicitly accesses user-specific Last.fm data such as recent tracks, loved tracks, weekly charts, and profile statistics, which can reveal personal habits, preferences, routines, and identity-linked behavioral data. The description and configuration do not clearly warn users that invoking the skill exposes personal listening-history data from their account, creating a privacy transparency issue and increasing the chance of unintended disclosure.

VirusTotal

66/66 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.