nushell-usage

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

• Third-party content exposure detected (high risk: 0.80). The skill includes examples that fetch and parse arbitrary URLs (see references/advanced-patterns.md's "robust-fetch" function and the "Parallel Processing" section which use http get $url and curl -s $url), so it clearly demonstrates ingesting untrusted third-party web content as part of its workflow.