ClawHub
Back to skill

Security audit

Learn Cog

Security checks across malware telemetry and agentic risk

Overview

This is a documentation-only tutoring skill that uses CellCog for educational help and does not show hidden, destructive, or unrelated behavior.

Install only if you trust CellCog and are comfortable using a CellCog API key. Avoid sending private student records, confidential documents, proprietary code, or regulated data unless CellCog's privacy and retention terms meet your needs.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • 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
Findings (1)

Vague Triggers

Medium
Confidence
89% confidence
Finding
The skill description is extremely broad ('every subject, every level') and does not provide clear trigger boundaries, which can cause over-invocation or inappropriate routing in agent ecosystems that rely on description matching. While not overtly malicious, this increases the chance that the skill is selected for tasks outside its intended scope, including sensitive domains like legal, security, or medical-style guidance, amplifying downstream risk.

VirusTotal

66/66 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.