make-api-shell-connection-workflow

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

• Third-party content exposure detected (high risk: 0.90). The skill's Retrieval and Discovery workflows (e.g., retrieval-execution.md and discovery-and-shells.md) explicitly instruct the agent to run Make API-call shells and "inspect the real output bundle" and return the app module response body (data: "{{3.body}}") for emails, CRM records, tickets and other SaaS data fetched from third-party provider APIs—i.e., untrusted/user-generated content the agent is expected to read and act on—so it can carry indirect prompt-injection risk.