033-architecture-diagrams

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

• Third-party content exposure detected (high risk: 0.70). The skill's required templates and rendering steps explicitly fetch and include public third-party resources (e.g., !include https://raw.githubusercontent.com/plantuml-stdlib/C4-PlantUML/... in the C4 templates and curl/download of plantuml.jar from GitHub), so the agent will retrieve and process untrusted external content that can influence diagram generation and tool behavior.

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

• Potentially malicious external URL detected (high risk: 0.90). The skill instructs operators to fetch and execute a remote PlantUML JAR at runtime (curl -L -o plantuml.jar https://github.com/plantuml/plantuml/releases/latest/download/plantuml.jar then java -jar plantuml.jar), which downloads and executes external code that the skill relies on for validation/rendering.