ClawHub
Back to skill

Security audit

Brainstorming

Security checks across malware telemetry and agentic risk

Overview

This skill is a disclosed CellCog brainstorming helper that sends user-directed prompts to CellCog and does not include hidden code or unsafe local behavior.

Install only if you intend to use CellCog as an external brainstorming partner. Treat anything you put in prompts, business metrics, files, or context as data shared with that service, and prefer using it for exploratory strategy work rather than routine local tasks.

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
90% confidence
Finding
The skill description is extremely broad, covering reasoning, problem-solving, strategic planning, research, documents, visuals, data, and prototypes. That breadth can cause accidental over-invocation on common user requests, routing general-purpose tasks into a third-party service and expanding unnecessary data exposure and agent surface area.

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.