map-user-flow

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

• Third-party content exposure detected (high risk: 0.85). At runtime, the skill’s required workflow reads and ingests user-provided free text via the Pre-Dispatch protocol’s cold-start/warm-start questions and then writes it into .forsvn/experience/*.md, which is subsequently loaded into the agent’s LLM context for later layers (e.g., structure/edge-case/diagram/wireframe/critic).