sparkscan-net-ios

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

• Third-party content exposure detected (medium risk: 0.65). The required runtime workflow includes a WebFetch of NuGet package pages (public web content) to read the latest stable version, and that fetched free-form page text can be ingested into the agent/LLM context, creating an indirect prompt-injection exposure path.

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

• Potentially malicious external URL detected (high risk: 0.90). The skill explicitly instructs the agent to WebFetch the NuGet page https://www.nuget.org/packages/Scandit.DataCapture.Barcode/ (with a fallback to https://api.nuget.org/v3-flatcontainer/scandit.datacapture.barcode/index.json) at runtime to read the authoritative package version and pin dependencies, so external content is fetched during runtime and directly influences the agent's generated code.