workflow-greenfield-init

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

• Third-party content exposure detected (high risk: 0.90). The required workflow in SKILL.md explicitly includes mandatory steps named "/web-research" and "/deep-research", which indicate the agent will fetch and consume open web / third‑party content as part of its decision-making and next-action workflow, exposing it to untrusted user-generated material that could carry indirect prompt injections.