multica-working-on-issues

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

• Third-party content exposure detected (medium risk: 0.65). The required runtime workflow involves reading GitHub PR title/body/branch text (outsider-authored by other users) via the webhook and then returning it through the multica issue pull-requests CLI/API, which can place that free text into the agent’s LLM context indirectly through the agent’s subsequent reasoning over PR content.