data-capture-sdk

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

• Third-party content exposure detected (high risk: 0.70). The skill explicitly instructs the agent to fetch live, public files from raw.githubusercontent.com (e.g., https://raw.githubusercontent.com/Scandit/data-capture-documentation/... ) as part of its required workflow to determine platform availability and features, which exposes the agent to untrusted third‑party web content that can materially influence its recommendations.

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

• Potentially malicious external URL detected (high risk: 0.80). Yes — the skill explicitly instructs fetching live content at runtime from raw.githubusercontent.com (e.g., https://raw.githubusercontent.com/Scandit/data-capture-documentation/main/src/data/products.json), and that fetched content is used to directly determine/drive the agent's recommendations (prompts), making it a required runtime dependency.