Security audit

Ads Asset Generator

Security checks for vulnerabilities and agentic risk

Overview

This is a plain advertising-creative planning skill with no code, installation behavior, credential access, persistence, or hidden data handling.

Installers should understand this skill may activate for some broad advertising or growth prompts, but its behavior is limited to producing ad creative briefs and testing plans. Review outputs for platform-policy accuracy and do not treat generated metrics or compliance outcomes as verified facts.

A.I.G

Vulnerability Patterns

Skill Instruction HijackingAlters the agent's session goals or safety constraints when the skill loads
Agent Memory PoisoningWrites attacker-controlled rules into memory that affect later sessions
Remote Payload Retrieval and ExecutionFetches external code whose behavior can change after review
Embedded Malicious CodeShips malicious scripts inside the skill and executes them locally
Unauthorized Access and Privilege EscalationObtains permissions beyond the task's legitimate needs

SkillSpector

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: 95% confidence
Finding: The trigger section is broad enough to match many generic business, marketing, and revenue-related requests, not just requests specifically needing ad asset generation. This can cause inappropriate skill invocation, leading the agent to steer users into specialized advertising outputs when a broader or different skill would be safer or more accurate.

Static analysis

No suspicious patterns detected.