Security audit
Security checks for vulnerabilities and agentic risk
This skill is coherent, but it should be reviewed because it can guide automated ad budget and bidding changes without a clear human approval gate.
Install only if you want an agent to help design operational paid-media automation policies. Keep it in advisory or monitoring-only mode unless explicit human approval, budget caps, rollback limits, audit logging, and platform-specific execution permissions are enforced outside the skill.
The skill does not prominently warn users that its outputs may influence live advertising spend through budget shifts, bid changes, freezes, and rollbacks. In a system that may operationalize skill outputs, missing this warning can lead to users authorizing or relying on impactful automation without understanding financial and business risk.
The activation conditions describe broad growth-orchestration scenarios but do not clearly separate this skill from other ads, analytics, or strategy skills. That ambiguity increases the chance that an agent routes routine advisory requests into a workflow that produces autonomous operational policies for live campaigns.
The trigger keywords are broad enough to match many ordinary marketing prompts, which can cause this high-impact automation skill to activate when a user may have intended a less autonomous planning skill. In this context, accidental activation is risky because the skill is designed to recommend budget, bid, scale, freeze, and rollback actions affecting live ad spend.
Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.
- Keep bid logic aligned with platform optimization objective.
## Constraints And Guardrails
- Do not auto-approve risky policy-sensitive creative changes.
- Keep manual override path always available.
- Every auto action must map to an auditable rule.
No suspicious patterns detected.