ClawHub
Back to skill

Security audit

Muse

Security checks across malware telemetry and agentic risk

Overview

Muse appears purpose-built for coding-history search and agent orchestration, but it asks for broad authenticated access to sensitive development history without enough in-skill privacy and scoping detail.

Install only if you intentionally want this provider's authenticated CLI to access or synchronize sensitive development history. Review the provider's privacy, retention, deletion, and sharing terms first; use project, current-directory, and time-range filters where possible; 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
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (3)

Vague Triggers

Medium
Confidence
87% confidence
Finding
The skill description is very broad and encourages use across a team's entire coding history, knowledge, and autonomous workflows without clearly defining activation boundaries or least-privilege conditions. In an agent ecosystem, this increases the chance the skill is invoked in contexts where sensitive project data, prior sessions, or team knowledge are unnecessarily exposed to the tool.

Missing User Warnings

Medium
Confidence
94% confidence
Finding
The description explicitly promises access to a team's entire coding history, past sessions, and knowledge base, but does not present a clear privacy or data-exposure warning. Because these data sources can contain proprietary code, credentials, internal discussions, and sensitive operational context, normalizing broad access without warning materially raises the risk of unintended disclosure and over-collection.

Missing User Warnings

Medium
Confidence
91% confidence
Finding
This section documents commands that can save, sync, extract, delete, import, and orchestrate project or knowledge-base content, but it does not warn users that these operations may modify local or remote data or transmit sensitive information. In the context of a tool designed to aggregate coding history and team knowledge, omission of such warnings makes accidental exfiltration, destructive changes, or overbroad synchronization more likely.

VirusTotal

63/63 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.