ClawHub

Muse

Security checks across malware telemetry and agentic risk

Overview

Muse is a coherent coding-memory skill, but it asks for very broad access to coding history, telemetry, knowledge-base sync, and autonomous agents without enough in-skill privacy and scope detail.

Install only if you intentionally want this provider's CLI to index or retrieve sensitive development history. Before enabling telemetry, sync, import, or autonomous-agent features, review the provider's privacy and retention terms, scope use to specific projects or time ranges where possible, and avoid syncing secrets, regulated data, or proprietary code unless your organization has approved 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 (2)

Missing User Warnings

Medium
Confidence
95% confidence
Finding
The skill explicitly advertises access to a team's 'entire coding history' and project context, but does not present a prominent, concrete privacy warning about what data may be collected, searched, or exposed through the CLI. In a security-sensitive agent context, this can lead users to authorize broad access to historical code, session data, and team knowledge without informed consent or understanding of retention and exposure risks.

Missing User Warnings

Medium
Confidence
97% confidence
Finding
The Telemetry section provides commands to enable data collection but does not warn users what telemetry contains, whether code/session content may be included, or what privacy consequences follow from enabling it. Because this skill centers on coding analytics and past session search, enabling telemetry without an explicit warning increases the risk of unintentionally collecting sensitive source code, secrets, prompts, or team activity metadata.

VirusTotal

63/63 vendors flagged this skill as clean.

View on VirusTotal