api-cms-strapi

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

• Third-party content exposure detected (high risk: 0.70). The skill's required examples and patterns explicitly fetch and ingest content from external Strapi APIs (e.g., fetch(${STRAPI_URL}/api/...) in examples/core.md and examples/auth.md and server-side reads via strapi.documents() in SKILL.md/backend examples), which are user-generated/untrusted CMS sources that the agent is expected to read and that can influence controller/service actions (publish, notify, update), creating a pathway for indirect prompt-injection.