shapeup

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

• Third-party content exposure detected (high risk: 0.90). The skill explicitly asks for an "external pitch (typically from Google Doc)" and requires the agent to "IMMEDIATELY run /frame-coach with the exact problem statement the user provided," meaning the agent will ingest and act on untrusted, user-provided third-party content from external docs (Stage 1: Framing), which can materially influence subsequent commands and decisions.