mfds-drug-safety

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

• Third-party content exposure detected (high risk: 0.90). The skill explicitly fetches public MFDS/OpenAPI data via the k-skill-proxy (see SKILL.md official endpoints and "Workflow" step 3) and the scripts' lookup_drugs() calls the proxy /v1/mfds/drug-safety/lookup and reads/interprets that JSON to inform interaction/decisions, so external third‑party content can materially influence behavior.