zio-http-knowledge

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

• Third-party content exposure detected (high risk: 0.95). The required runtime workflow fetches public documentation text from https://ziohttp.com/llms.txt (and then other ziohttp.com/*.md pages), which is outsider-authored free text ingested into the agent’s LLM context via web fetching.

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

• Potentially malicious external URL detected (high risk: 1.00). The skill explicitly requires fetching the runtime sitemap at https://ziohttp.com/llms.txt (and then fetching .md pages from ziohttp.com or the combined file https://ziohttp.com/llms-full.txt, with GitHub fallbacks) and uses that fetched content to drive routing and answers, so external content directly controls the agent's prompts and responses.