reconcile

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

• Third-party content exposure detected (high risk: 0.85). SKILL.md’s required workflow pulls outsider-authored free text from GitHub issues/epics (e.g., gh issue list ... --json ... ,body and gh issue view ... --json ... ,title), and that body/title text is then used to generate proposed Goal/Why/ADR content that is fed back into the agent’s LLM context for user confirmation.