project-diagrams

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

• Potentially malicious external URL detected (high risk: 1.00). The skill makes runtime calls to the OpenRouter API (https://openrouter.ai/api/v1/chat/completions) and uses the model's review output to decide on regeneration and to programmatically modify/improve prompts, so fetched external content directly controls agent instructions and is a required dependency.