ClawHub
Back to skill

Security audit

Ads Brain Planning Optimize Pipeline 1.0.0

Security checks across malware telemetry and agentic risk

Overview

This skill is a documented ad-optimization planning guide that collects relevant ad evidence and produces recommendations without installing code or directly changing campaigns.

Installers should be comfortable with the skill using ad-account performance summaries, audience insights, creative data, and forecast tools to make optimization recommendations. It should remain advisory unless a separate execution-confirmation system approves changes, and teams serving non-Chinese users should add a clear language fallback.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • 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
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
Findings (1)

Natural-Language Policy Violations

Medium
Confidence
88% confidence
Finding
The skill hard-requires Chinese-only customer-visible output and explicitly forbids other language forms, but it does not provide a user-language negotiation path or document a justified locale restriction. In a multi-language agent environment, this can cause unsafe misunderstanding of optimization advice, risk warnings, or execution-confirmation steps for users who are not proficient in Chinese, reducing informed consent and increasing the chance of operator error.

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.