Security audit
Security checks for vulnerabilities and agentic risk
This is a disclosed ad-campaign planning workflow with guardrails and no bundled executable code or persistence.
Install this only where a Chinese-language ad planning workflow is appropriate. Review generated campaign drafts and warnings before confirming any downstream creation action, especially budget, audience, objective, and eligibility assumptions.
The trigger conditions are written broadly enough to match generic planning/help requests, which can cause this skill to activate outside its intended scope. In this skill’s context, unintended invocation matters because it can route users into a create pipeline that produces campaign drafts or creation parameters when they may have wanted advice, diagnosis, or another workflow instead.
Forcing all customer-facing output to Chinese without checking user locale or preference can cause misunderstandings of constraints, warnings, or next steps. In an ad-creation workflow, misread gating outcomes or assumptions can lead to incorrect confirmation, poor campaign setup decisions, or inaccessible output for non-Chinese-speaking users.
