jetson-set-target

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

• Third-party content exposure detected (medium risk: 0.65). Outsider-authored free text can enter the LLM context via parsing and displaying target-platform/*.yaml profile contents (e.g., reference_devkit.name / custom_carrier.name and flash_config) that may have been authored by someone other than the operating user; the skill reads these YAMLs at runtime and prints summaries to the user/LLM.