creating-mermaid-diagrams

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

• Third-party content exposure detected (low risk: 0.10). The required runtime workflow only ingests the user’s request to generate .mmd and then validates/exports it locally or by POSTing that generated Mermaid text to Kroki; it does not read arbitrary outsider-authored free text from external sources without first generating a specific diagram.

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

• Potentially malicious external URL detected (high risk: 0.70). The skill issues runtime curl requests to Kroki (e.g., https://kroki.io/mermaid/svg, https://kroki.io/mermaid/png, https://kroki.io/mermaid/pdf), which invoke a remote renderer (i.e., execute remote code) to produce diagrams during skill execution.