ClawHub
Back to skill

Security audit

Metacognition Checker

Security checks across malware telemetry and agentic risk

Overview

The available evidence shows a clean scan and only a localization concern, not behavior that would put user data or the system at risk.

Safe to install based on the available evidence. Review whether you are comfortable with any Chinese-only instructions or examples; otherwise there is no artifact-backed security concern requiring Review.

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
96% confidence
Finding
This markdown file includes a substantial Chinese-only section and examples, but the skill does not state that it is bilingual or ask the user which language they prefer. That can force a specific language/locale experience on users without opt-in, which matches the language-policy violation criteria.

VirusTotal

63/63 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.