continuous-improvement-engine-scott-margetts

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

• Third-party content exposure detected (high risk: 0.75). The skill’s REQUIRED runtime workflow for Mode 1 ingests user-pasted “trigger event” documents (e.g., RAID updates, scope change notices, LC/status report extracts) as free-form text into the LLM context, and those pasted materials are explicitly allowed to be authored by other parties (outsider) such as counterparties/LC/client communications, creating an indirect prompt-injection path.