pulumi-debug-failed-operation

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

• Third-party content exposure detected (high risk: 0.70). SKILL.md instructs fetching Pulumi Cloud engine event diagnostics via pulumi api .../update/<version>/events or .../preview/<preview-id>/events and extracting .events[].diagnosticEvent.message, which is free-form text authored by Pulumi/provider/program execution (i.e., not authored by the operating user), creating an indirect prompt-injection path into the agent’s LLM context.