ClawHub
Back to skill

Security audit

Brainstorming Strategy Cellcog

Security checks across malware telemetry and agentic risk

Overview

This skill is a disclosed CellCog brainstorming helper that sends user-directed prompts to an external CellCog agent, with no hidden local actions in the submitted artifact.

Install only if you are comfortable using CellCog as an external agent provider. Treat prompts, business details, code snippets, and files you share in CellCog chats as data sent to that service, and prefer targeted prompts so the broad skill description does not pull it into ordinary tasks unnecessarily.

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 and covers generic reasoning, problem-solving, planning, research, documents, visuals, data, and prototypes. In systems that route or invoke skills from natural-language descriptions, this kind of expansive wording can cause unintended selection for ordinary user requests, increasing the chance that the skill is over-invoked and gains access to contexts or workflows beyond its narrowly intended purpose.

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.