paid-ads-strategy

Security checks across malware telemetry and agentic risk

Overview

This is an instruction-only paid advertising strategy skill with no code, install hooks, credential access, or direct ability to spend money.

Safe to install as a planning skill. Review local project-context files for sensitive business details before use, and require explicit approval before invoking downstream ad-platform skills that could create campaigns, change public ads, or spend budget.

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 trigger is extremely broad and includes many generic marketing and advertising terms, so it may be invoked for routine discussions that do not actually require this specialized skill. Over-broad routing can cause unintended context capture, inappropriate delegation, or disclosure of project context files to the wrong workflow, which is a real security and privacy concern in agent systems even without malicious intent.

VirusTotal

51/51 vendors flagged this skill as clean.

View on VirusTotal