you-web-search

HIGH W007: Insecure credential handling detected in skill instructions.

• Insecure credential handling detected (high risk: 1.00). The skill's example API call embeds the API key into a curl header ("-H "X-API-Key: {YDC_API_KEY}""), which instructs including a secret value verbatim in generated commands and thus risks secret exposure.

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

• Third-party content exposure detected (medium risk: 0.30). The skill’s required runtime workflow reads outsider-authored free text from You.com’s Search API response—specifically the returned titles/snippets (and optionally live-crawled page content) are parsed via /tmp/youcom-search.json using jq in Phase 1 “Response Processing” and then formatted for delivery.