reconcile

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

• Third-party content exposure detected (high risk: 0.70). The required runtime workflow reads review-NNN.md (which contains the reconciliation brief) and then uses its text to author REV rows and manual edits; since review-NNN.md is an outsider-authored artifact (audit output from another party), its free-form reconciliation brief text can be injected into the agent’s LLM context via the “Read inputs” step.