Security audit

Ads Asset Manager

Security checks for vulnerabilities and agentic risk

Overview

This is a documentation-only advertising creative planning skill with no code execution, persistence, credential use, or hidden data access.

Installers should treat this as a benign ad creative planning skill. The main practical caveat is that it may activate on broad growth or marketing prompts, so users should confirm that its recommendations are being applied only to ad creative asset workflows and not mistaken for authorized ad-account actions.

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 conditions are broad enough to match many generic business, growth, and marketing requests, causing the skill to activate outside its narrowly stated purpose. Overbroad routing can misapply specialized ad-execution guidance in contexts where it is not appropriate, increasing the chance of irrelevant, unsafe, or overly action-oriented recommendations.

Static analysis

No suspicious patterns detected.