omni-combos-routing

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

• Third-party content exposure detected (low risk: 0.10). The skill’s runtime workflow exposes only first-party configuration/API usage (REST endpoints like /api/combos, /api/fallback/chains, /api/routing/simulate) and does not describe any mechanism where outsider-authored free text is ingested without the agent first selecting a specific combo/record to act on.