ad-creative

MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).

• Third-party content exposure detected (high risk: 0.70). This skill's SKILL.md explicitly instructs the agent to pull user-generated review snippets from public sites ("Pull from G2, Capterra, Trustpilot for real quote snippets") and the workflow expects ingesting third‑party performance data via platform integrations, meaning it reads untrusted public/user-generated content that can influence ad-generation decisions.