ClawHub
Back to skill

Security audit

skill-navigator

Security checks across malware telemetry and agentic risk

Overview

This skill is a disclosed helper for choosing among already installed local skills and does not itself execute tasks or hide high-impact behavior.

Install only if you are comfortable using the `aide-skill-manager` npm package and allowing `skm` to maintain a catalog of your installed Claude/Codex skills. Non-Chinese users may need to ask the agent to answer in their preferred language.

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)

Natural-Language Policy Violations

Medium
Confidence
97% confidence
Finding
Line L58 states that when relaying output to the user, the agent should use Chinese. This imposes a language preference on all users and does not provide any opt-in, opt-out, or locale-selection mechanism, which is a natural-language policy concern.

VirusTotal

63/63 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.