gbp-api-automation

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

• Third-party content exposure detected (high risk: 1.00). The skill explicitly instructs the agent to fetch and process user-generated GBP content (e.g., "Fetch new reviews for all locations" in the "Review Monitoring" workflow and references to the My Business Q&A API and review/post/photo handling in SKILL.md), which are untrusted third-party inputs that the agent is expected to read, interpret, and act on (routing responses, queuing actions), enabling indirect prompt-injection risk.