ClawHub
Back to skill

Security audit

grill-with-docs

Security checks across malware telemetry and agentic risk

Overview

This skill is a planning workflow that combines brainstorming and domain modeling, with disclosed document-writing outputs and no hidden execution behavior.

Install this if you want an agent to run a structured planning conversation and update project documentation. Before invoking it, be clear that you want the full brainstorming plus domain-modeling workflow, since it may produce or modify design docs, CONTEXT.md, and ADR files.

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
92% confidence
Finding
The skill’s activation example is overly broad: a generic request like wanting to design a new feature can trigger the skill without clear scope boundaries or user confirmation. In an agent ecosystem, this increases the chance of inappropriate invocation, causing the agent to load additional skills and modify project artifacts such as design docs, CONTEXT.md, or ADRs in contexts where the user did not explicitly request this workflow.

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.