form-workflow

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

• Third-party content exposure detected (high risk: 0.90). The workflow's Step 2 explicitly instructs the agent to use the rebyteai/internet-search sub-skill to fetch industry best practices and "competitor form examples" from the open web, which the agent will read and use to shape form design and behavior, exposing it to untrusted third-party content that could carry indirect prompt injection.