strapi-version-upgrade

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

• Third-party content exposure detected (high risk: 0.75). The required workflow fetches breaking-change documentation from the public web at runtime (e.g., https://docs.strapi.io/.../breaking-changes.md) and then ingests that fetched Markdown into the agent’s LLM context via WebFetch, which is outsider-authored free text.

MEDIUM W012: Unverifiable external dependency detected (runtime URL that controls agent).

• Potentially malicious external URL detected (high risk: 0.80). The skill instructs fetching the Strapi breaking-changes Markdown at runtime via https://docs.strapi.io/cms/migration/v4-to-v5/breaking-changes.md (via WebFetch) and using that fetched content to drive the agent's upgrade guidance, which means external content is fetched at runtime and directly controls the agent's output.