post-mortem

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

• Third-party content exposure detected (high risk: 0.85). The required workflow has the author “fill in … Timeline scaffold from the incident chat transcript” and “interviews everyone who took an action” (outsider-authored incident chat messages and interviewees’ free-form answers), which would be ingested into the LLM context as prose during drafting.