hono

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

• Third-party content exposure detected (high risk: 0.90). SKILL.md explicitly instructs the reader/agent to "Read it before writing Hono code" and to fetch files from the public GitHub repo (https://github.com/yusukebe/hono-skill) and the public docs at hono.dev, meaning the agent is expected to ingest and act on untrusted, user-generated third-party content that could influence its decisions.