Back to skill

Security audit

Ads Optimizer

Security checks for vulnerabilities and agentic risk

Overview

The skill is coherent for ad management, but it can change live campaign settings and spend without clear approval, dry-run, rollback, or scope limits.

Use this only where agents are allowed to manage paid media. Before installing, require strict account scope, human approval for mutating actions, budget limits, audit logs, and a rollback process for campaigns and tests.

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
Vulnerability Patterns
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
  • 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 (2)

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The skill exposes campaign creation and update functionality that can directly affect live advertising configuration and downstream spend, but the description does not warn operators that using it can change production campaign behavior. In an agentic setting, this increases the risk of unintended budget changes, targeting drift, or live campaign disruption because a user or orchestrating agent may treat the skill as read-only or low-risk analytics.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
92% confidence
Finding

The A/B testing and optimization portions describe actions that can alter traffic allocation, bids, keywords, or other performance-sensitive settings without prominently warning that campaign outcomes and spend patterns may change. For autonomous or semi-autonomous agents, this omission is dangerous because optimization recommendations and tests may be interpreted as safe analysis rather than actions that can materially shift live delivery and business results.

Content

No source excerpt is available for this finding.