agency

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

• Third-party content exposure detected (high risk: 0.90). The skill's "sync-upstream" workflow (Step 6) explicitly compares local forked agents/skills with "moai upstream" versions and may fetch/apply upstream diffs (reading .agency/fork-manifest.yaml and .claude/skills/moai-*), so untrusted third-party upstream content would be ingested and could directly change agent behavior.