fmt-json-flatten

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

• Third-party content exposure detected (medium risk: 0.30). The required runtime workflow posts user-supplied JSON (the json field from the caller) to the first-party endpoint https://fittings.sh/v1/fmt/json-flatten, and the client (call.mjs) ingests and transmits that free text at runtime; this is direct outsider-authored free text ingestion rather than passive documentation browsing.

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

• Potentially malicious external URL detected (high risk: 1.00). The skill instructs fetching and running remote code via curl -sO https://fittings.sh/skill/call.mjs (downloaded at runtime if call.mjs is missing), which would execute remote script content and is a required dependency.