ClawHub
Back to skill

Security audit

AI Brand Analyzer

Security checks across malware telemetry and agentic risk

Overview

This skill appears to do what it says: it uses Gemini and Google Search to create brand profile JSON files, with disclosed save options.

Install only if you are comfortable using a Gemini API key and sending brand-analysis prompts to Google/Gemini. Prefer stdout or a deliberate project-local --output path first, and use --auto-save only when you want the generated profile written into the Ad-Ready catalog.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Findings (3)

Lp3

Medium
Category
MCP Least Privilege
Confidence
90% confidence
Finding
The skill documents use of environment variables and file writes (`GEMINI_API_KEY`, `--output`, and `--auto-save`) but declares no corresponding permissions. That mismatch can cause the agent to perform sensitive actions without explicit user-visible authorization boundaries, especially when writing into fixed locations like `~/clawd/ad-ready/configs/Brands/`.

Vague Triggers

Medium
Confidence
82% confidence
Finding
The description is broad enough to activate on generic creative or ad-generation requests, not just explicit brand-analysis tasks. Overbroad routing increases the chance the skill runs in contexts where users did not intend external research, profile creation, or persistent storage, which can lead to unnecessary data collection and file modification.

Vague Triggers

Medium
Confidence
85% confidence
Finding
The 'When to Use' conditions include subjective triggers like running before Ad-Ready or when a brand 'doesn't have a profile yet,' without clear user-consent boundaries. In this context, ambiguity is more dangerous because the skill can research external sources and write persistent files, so accidental invocation could trigger networked analysis and storage beyond the user's expectation.

VirusTotal

66/66 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.