holoscan-setup

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

• Third-party content exposure detected (high risk: 0.85). The required workflow fetches public NVIDIA documentation at runtime (Step 1: https://docs.nvidia.com/holoscan/sdk-user-guide/), which is outsider-authored free text that can be ingested into the agent’s LLM context.

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 at runtime to fetch and use https://docs.nvidia.com/holoscan/sdk-user-guide/ (and its sdk_installation.html) to determine supported platforms and drive install recommendations, so this external URL directly controls the agent's instructions during execution.