matlab-deploy-embedded-ai

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

• Third-party content exposure detected (low risk: 0.10). The skill’s runtime workflow can read outsider-authored free text because it may require (as part of function-signature lookup) web browsing of MathWorks reference pages, which are not guaranteed to be trusted/benign content in every context.

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

• Potentially malicious external URL detected (high risk: 0.90). The skill explicitly tells the agent to fall back to web-browsing and fetch function reference pages at runtime from https://www.mathworks.com/help//ref/.html, which will load external content into the agent's context to drive prompt behavior and output formatting.