generating-dotnet-sdks

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

• Third-party content exposure detected (high risk: 0.90). The skill explicitly fetches and ingests arbitrary public web content (e.g., autosdk generate/ init accept OpenAPI spec URLs and the generate.sh examples use curl to download specs, and autosdk ai spec-from-docs scrapes HTML docs via Firecrawl), so untrusted third‑party documentation/specs are read and used to drive code generation and subsequent actions.

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

• Potentially malicious external URL detected (high risk: 0.80). The autosdk "ai spec-from-docs" command fetches and scrapes an arbitrary documentation URL at runtime (e.g., https://docs.example.com/api) via Firecrawl and feeds the scraped HTML into OpenAI GPT-4o to produce an OpenAPI spec, which injects remote content into the model context and therefore directly controls model output at runtime.